MLOps/Systems • Score 85
Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
arXiv:2608.12476v1 Announce Type: new
Abstract: Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records may support an outgoing claim. We introduce Governed Persistent Memory (GPM), an auditable bitemporal state-transition model with source-bound admission, derived lifecycle state, current public barriers, and fail-closed structured release. Five executable clauses cover ledger integrity, source binding, conflict isolation, non-revival after retraction or deletion, and exact claim closure over a fresh view at one verified head.
On a prespecified hash-frozen 3,600-case GPM-ReleaseBench, GPM matches all complete outcomes; the strongest of three intentionally simple complete policies matches 1,800/3,600 and makes unmatched releases on 50% of violation cases. A separate sealed end-to-end service evaluation exercises real ingestion and release across eight query families. In its publicly disclosed V3 arm, the governed lane is correct on 2,400/2,400 clusters versus 600/2,400 for ungoverned local Qwen2.5-7B; it repairs all 1,800 baseline failures with no regression (one-sided 95% lower bounds 99.875% and 99.834%). A later V5 reseal over Chinese- and English-command arms, with generation-date pinning and no post-freeze reducer amendment, again obtains 2,400/2,400 per arm. A production-code-independent finite model explores 331,776 semantic and 1,990,656 query states without a full-contract counterexample, and a 100,000-trace three-engine differential yields zero mismatches.
These are bounded contract and implementation results, not open-world model accuracy or evidence of world truth. Governed answers in the sealed service evaluation are deterministic service outputs; the 7B result is the ungoverned comparison, not a claim that a language model itself became perfectly accurate.
Source: arXiv cs.AI
Vision • Score 85
FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
arXiv:2608.12932v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four. Visual encoding wastes compute on overlapping video frames; language-model prefill recomputes context that could be carried over from the previous timestep; reasoning tokens are generated serially despite low entropy; and flow-matching denoising applies uniform compute to a non-uniform velocity field. Addressing any one stage in isolation leaves the others untouched. We propose FlashDrive, an algorithm-system co-design framework that targets all four stages simultaneously. Our key insight is that each bottleneck admits a distinct, lightweight algorithmic shortcut: temporal overlap enables streaming KV-cache reuse across frames; the low per-token entropy and strong intra-block correlations of driving-domain reasoning make a non-autoregressive diffusion drafter highly effective for speculative decoding; and the velocity field's structure---sharp at the endpoints, flat in the middle---permits adaptive step caching that concentrates compute where it matters. Layered on system-level CUDA Graph compilation and kernel fusion, these techniques compound. Applied to Alpamayo 1.5-10B with W4A8 quantization, FlashDrive reduces end-to-end latency from 717ms to 151ms (4.7x) while leaving accuracy essentially unchanged: minADE6@6.4s shifts by only 0.08m, minADE1 improves, and closed-loop collision and off-road rates improve in simulation. By raising a 10B-parameter reasoning VLA from 1.4~Hz to 6.6~Hz on a single GPU, FlashDrive moves end-to-end autonomous driving substantially closer to real-time deployment.
Source: arXiv cs.AI
NLP/LLMs • Score 85
Multiview Representation Learning via Distributed Joint Latent Space Structuring
arXiv:2504.18455v2 Announce Type: replace
Abstract: We study distributed multiview representation learning, a problem in which $K$ clients each observe a distinct but possibly statistically correlated view. The clients independently extract local representations from their views, which are then used by a central decoder for joint target estimation. One central difficulty is that, since the clients are not allowed to communicate with each other, they must autonomously decide what to encode. We study this coordination problem from a generalization error perspective. For both classification and regression tasks, we derive novel generalization bounds expressed in terms of the Minimum Description Length (MDL) of the joint latent variables across all views and across both training and test datasets. Our structure-aware bound reveals that statistical correlations among the extracted representations tighten the bound, providing theoretical grounding for the empirically observed benefits of cross-view feature alignment. Perhaps counterintuitively, our findings imply that encoders may benefit from extracting redundant representations. Motivated by these bounds, we introduce a data-dependent Gaussian product mixture prior that can be learned and applied in a fully distributed manner. The joint structure of this multiview prior captures inter-view dependencies that are typically discarded by marginal-only approaches. Comprehensive experiments across multiple datasets, encoder architectures, numbers of views, and distortion settings demonstrate the effectiveness of our proposed approach.
Source: arXiv stat.ML
Multimodal • Score 85
From Visual Widgets to UI Code: Efficient Tool-Grounded Generation
arXiv:2608.12611v1 Announce Type: new
Abstract: Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipelines reduce such errors through component-wise decomposition, predefined templates, and customized intermediate representations. These structures, however, introduce additional generative orchestration and restrict outputs to designs covered by the representation. We investigate whether selective tool grounding can improve the fidelity--efficiency trade-off of direct widget-to-code generation. We introduce \textbf{WidgetGen}, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScript XML (\emph{JSX}). This design reduces reliance on component-wise generation while avoiding a fixed UI schema. Across six multimodal models and \(1{,}000\) held-out widgets, WidgetGen outperforms direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics, with consistent gains in area, legibility, and style. Finally, reconstruction-derived image-code pairs improve six Qwen-family open-weight models across every reported metric through supervised fine-tuning. These results establish WidgetGen as a strong lightweight baseline and show that selective evidence grounding offers an effective alternative to extensive representation constraints.
Source: arXiv cs.CV
MLOps/Systems • Score 85
Correct Is Not Governed: Provenance Integrity in Agentic Workflows
arXiv:2608.12761v1 Announce Type: new
Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim, or work made stale by a later change. We define governed execution as work whose decisions, completion, and response to change are supported by inspectable provenance. We present Matrix, a deterministic causal-state layer that records authority and fact dependencies, verifies completion evidence, and selectively invalidates affected work. Across controlled comparisons, governed and direct workflows often reached the same outcomes, but only the governed path consistently preserved governing evidence, refused unsupported closure, and limited recovery to dependent tasks. A role-separated transfer challenge then failed: a deterministically enforced completeness contract severely over-blocked synthetic packets produced outside its authoring context. These results do not establish Matrix as a general accuracy enhancer; they support its primary role as an institutional integrity layer for making agentic work auditable and independently verifiable.
Source: arXiv cs.AI
Multimodal • Score 92
A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings
arXiv:2608.12745v1 Announce Type: new
Abstract: Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific models on the edge transform raw medical data into compact structured outputs, while a cloud LLM synthesizes these outputs into clinical summaries. An LLM-based orchestrator dynamically selects diagnostic tools based on patient context, promoting comprehensive modality coverage without processing irrelevant inputs. We evaluate on 20 multimodal clinical cases spanning cardiac, obstetric, trauma, and screening scenarios under three simulated network profiles (500,kbps--5,Mbps). The hybrid system achieves 98--99% diagnostic tool recall with 92--96% precision, matches or exceeds cloud-only baselines on clinical accuracy, and maintains bandwidth-invariant latency (25--35,s) at 4--15x lower token cost. These results highlight the role of architectural design in enabling efficient multimodal integration and improving factual grounding compared to cloud-only approaches under deployment constraints.
Source: arXiv cs.LG
MLOps/Systems • Score 85
CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution
arXiv:2608.12629v1 Announce Type: new
Abstract: GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black box and receive only errors, correctness outcomes, and timing, while existing DSLs either hide critical scheduling decisions or expose them through difficult layout abstractions. We present CAKE, a compiler-agent co-design in which agents author CAKE IR, a typed, hardware-explicit schedule representation. CAKE exposes warp roles, memory movement, synchronization, and pipelines while supporting verification, cost modeling, and localized diagnostics. The harness itself evolves: recurring failures become verifier rules, IR primitives, model calibrations, and reusable optimization tactics. In matched implementation-hidden Flash-KMeans clean starts on B200, the best CAKE IR candidate at an 80-million-token budget runs at 1.144x the tuned FlashML baseline, compared with 0.928x for direct CUDA/PTX. Beyond this benchmark, agent-generated Kimi Delta Attention achieves a 2.05x geometric-mean speedup over official FlashKDA and passes end-to-end serving validation. Dispatcher-backed KNN and KMeans improve performance by 1.42x to 2.12x across more than 400 shapes, and four kernel changes are available as upstream PRs. CAKE targets NVIDIA GPUs from Ampere through Blackwell and separates single-shape evolution from library generalization and dispatch.
Source: arXiv cs.LG
NLP/LLMs • Score 85
BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs
arXiv:2608.13046v1 Announce Type: new
Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans typically provide an initial problem, agents deliberate internally, and the system returns a final response. BoardroomAI instead treats the human as a persistent participant who can intervene by challenging assumptions, modifying constraints, changing priorities, introducing evidence, or redirecting the decision process. We operationalize this human--agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Across 600 generated decision-DAG interventions, propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions show that correct intervention routing may still provide insufficient context for synthesis, motivating a \emph{decision-sufficient context closure} for human-steered multi-agent deliberation. All results are synthetic and prototype-level.
Source: arXiv cs.AI
MLOps/Systems • Score 85
CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
arXiv:2608.12842v1 Announce Type: new
Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining. However, parameter conflicts and knowledge interference across tasks often degrade merged-model performance. Prior work introduced Conflict-Aware and Balanced Sparsification (CABS), which reduces parameter interference through structured pruning and sequential masking. However, CABS relies on grid search to determine scaling coefficients, resulting in exponential time complexity, while its optimization objective can be dominated by high-performance tasks, leading to suboptimal overall performance. To address these limitations, we extend CABS and propose CABS+. Specifically, Adaptive Weight Allocation (AWA) optimizes merging coefficients via a gradient-free search scheme to reduce time complexity, while an asymmetric fitness function promotes more comprehensive performance gains across tasks. Moreover, we conduct a systematic empirical study of key factors influencing model merging performance and propose Relative Synergy Score (RSS) to quantify model mergeability and guide model selection. We compare CABS+ with state-of-the-art model merging methods, including CABS, AdaMerging, and WUDIMerging, across 27 datasets and 5 models covering large language, small-scale language, and vision models. Extensive experiments verify the effectiveness and efficiency of CABS+. Compared with AdaMerging and WUDIMerging, CABS+ improves overall performance by 16.97% and 12.93%, respectively, exhibits stronger stability and robustness across varying task numbers and model architectures, uses less than 25% of the GPU memory required by AdaMerging, and achieves nearly a 4x speedup in merging time over WUDIMerging.
Source: arXiv cs.AI
NLP/LLMs • Score 90
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
arXiv:2608.12990v1 Announce Type: new
Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preserve coherent event-level and temporal evidence compared with fixed-window batching. The resulting records are organized with lightweight structured indexes for query-planned evidence retrieval. Experiments using GPT-4.1-Mini show that LycheeMemory achieves state-of-the-art performance, reaching 89.22% on LoCoMo and 92.20% on LongMemEval-S. Compared with A-Mem, it reduces construction tokens by 86.0% on LoCoMo and 75.9% on LongMemEval-S without increasing query-time token usage. More broadly, our results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated.
Source: arXiv cs.CL
NLP/LLMs • Score 85
Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention Matching
arXiv:2608.12331v1 Announce Type: new
Abstract: Reasoning language models generate lengthy chain-of-thought (CoT) sequences whose key-value (KV) cache grows linearly and becomes a memory bottleneck during decoding. Existing compaction methods treat reasoning trajectories as flat token sequences and apply uniform compression, ignoring the hierarchical structure of CoT reasoning where different steps vary drastically in importance. We propose \textbf{Thought-Aware Attention Matching (TAM)}, which exploits this structure through three mechanisms: (i)~thought segmentation that decomposes the trajectory into reasoning blocks, (ii)~adaptive budget allocation that assigns compression budget based on each segment's importance and size, and (iii)~pivotal token protection that preserves high-attention reasoning anchors. We prove that the allocation rule is optimal under a convex error model and that cumulative error under sequential compaction remains bounded. Experiments on AIME 2024 and MATH-500 with Qwen3-4B show that TAM improves accuracy over uniform compaction at the same memory footprint, with periodic compaction bounding peak memory to 3.1--3.2\,GB (a 65\% reduction) while maintaining competitive accuracy.
Source: arXiv cs.CL
MLOps/Systems • Score 85
Designing AI Pipelines for Decision-Ready ITSM Intelligence
arXiv:2608.12670v1 Announce Type: new
Abstract: IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are difficult for sales and executive stakeholders to convert into actionable intelligence. This paper presents a sociotechnical AI pipeline, designed and evaluated following design science research principles, that transforms raw ITSM exports into a multilevel decision-support artifact. The pipeline combines LLM-based schema normalization, HDBSCAN sub-topic clustering, and hierarchical agglomerative clustering to generate executive-facing Main-topics and granular Sub-topics. A stakeholder evaluation across six artifacts and five raters from Sales Engineering and customer success roles shows that all four decision-support metrics, interpretability, actionability, trust, and likelihood of use, on average exceed 4.0 out of 5.0, with trust as the most consistent signal. The findings position ITSM analytics as an Information Systems (IS) problem of transformation, abstraction, and human-centered design.
Source: arXiv cs.AI
RL • Score 85
Multi-AUV Ad-hoc network-based Target Tracking: A Value Gradient Guidance Multi-Agent Diffusion Reinforcement Learning Approach
arXiv:2608.12436v1 Announce Type: new
Abstract: Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under constrained acoustic communication, dynamic topology, and uncertain ocean disturbances. Although multi-agent reinforcement learning (MARL) enables decentralized coordination through centralized training, existing methods suffer from high-dimensional joint state-action modeling, noise-sensitive policy generation, leading to unstable training and degraded tracking. To address these issues, we propose VGG-MADiffRL, a value-gradient-guided multi-agent diffusion RL algorithm, and MDCA, a diffusion?based hierarchical control architecture. Leveraging underwater mission characteristics, we model sonar detection mechanisms and ocean current disturbances, formulating cooperative tracking for multi-AUV ad-hoc networks as an MDP. The proposed MDCA constitutes a three-tier closed-loop control framework: a global intelligent control layer, a local online training layer, and a physical action execution layer. This structure enables synergistic optimization across task allocation, local decision processes, and execution feedback. Within MDCA, the local online training layer is the policy learning framework; VGG-MADiffRL builds on diffusion policies and incorporates value gradients to guide action generation in the reverse denoising process, steering the generated actions towards higher expected returns. It employs twin value networks with joint optimization and soft target updates to mitigate overestimation and training oscillations, promoting more stable convergence. Experimental results show that VGG-MADiffRL consistently achieves faster convergence, higher tracking accuracy, and smoother training dynamics in cooperative tracking scenarios, validating its effectiveness and practical engineering value in dynamic underwater settings.
Source: arXiv cs.LG
NLP/LLMs • Score 85
PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping
arXiv:2608.12600v1 Announce Type: new
Abstract: A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization in diverse environments. To address this limitation, we propose a teacher-student semi-supervised learning (SSL) framework that generates high-quality pseudo-labels from unlabeled data through confidence-aware map refinement. Our approach first trains a teacher model on limited labeled data, then leverages Beta-distribution-based confidence maps to assess the reliability of predicted map elements across temporal observations. Unlike conventional filtering methods that discard entire elements, we introduce a spatial clipping technique that selectively preserves high-confidence regions while removing unreliable segments. The refined map elements serve as map priors that improve the teacher model's prediction accuracy on unlabeled data in a second pass. These enhanced predictions become pseudo-labels for training a student model from scratch, followed by fine-tuning on the original labeled data. Experimental results on the nuScenes dataset demonstrate that our teacher-student framework with refined pseudo-labels improves performance by +6.1 mAP under a low-label regime compared to training on labeled data alone, offering a practical solution to the labeled data scarcity problem in online HD map construction.
Source: arXiv cs.CV
MLOps/Systems • Score 85
@skills: Attention is all you have
arXiv:2608.12610v1 Announce Type: new
Abstract: There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the system prompt, competing for fewer than 100 reliable trigger slots. This leaves the long tail with no practical path to use and forces teams' own playbooks to compete for the same scarce space. We observe that installation bundles three separable functions: content, persistence, and automatic triggering. Only the last requires prompt residency. We therefore propose @skills, an open protocol that separates them. A path addresses any skill, subtree, or collection, and reading a skill is sufficient to use it, so nothing is installed or made resident. The operation vendors a copy at the same path into a project's Git-tracked tree for adaptation and ownership. The operation adds one .gitignore-style line, the only element that costs prompt residency. A directory is a menu, making bundles ordinary directories rather than all-or-nothing units. The protocol requires no manifest, lockfile, or registration, and SKILL.md remains unchanged. @skills is additive, ships as an installable package, and turns any agent that can read files and run commands into a client through a single instruction file. Its open specification is at https://github.com/SylphAI-Inc/atskills and it is implemented in the AdaL CLI at https://adalagent.ai . Because paths address skills well but cannot find them, the protocol is paired with a free hub at https://atskills.one for corpus-wide search and ranking, repository-free hosting, private and team collections, and one-screen authoring. The hub is optional: gh: and local paths resolve without it, and indexed GitHub skills retain their gh: identities. Install less, use more.
Source: arXiv cs.AI
Theory/Optimization • Score 85
Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
arXiv:2608.12597v1 Announce Type: new
Abstract: Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen random map. This raises a practical question: how large must the latent search space be to reach a low-loss region? We first express the known accessibility transition in an equivalent conic form, centered for compact convex targets at the statistical dimension of the polar cone. Our main theoretical contribution is an orientation-resolved quadratic master formula that predicts the random-slice residual from both the curvature spectrum and the reference-to-solution displacement profile. It yields a self-consistent isotropic-orientation predictor and, in a conservative radius-only specialization, recovers the earlier Gaussian-width quadratic bound. Building on this analysis, we introduce Random Mapping Networks (RaMaN), which instantiate the predicted latent dimension using structured Hadamard or seed-regenerated Gaussian maps. These constructions avoid the O(dP) storage of dense random maps and reduce optimizer-state memory from O(P) to O(d). We also develop matrix-free curvature approximations and sweep-free dimension selection. Across controlled quadratic and neural-curvature experiments, the orientation-resolved predictor closely tracks measured transition locations and outperforms orientation-agnostic approximations when displacement direction matters. End-to-end experiments further show sharp, protocol-dependent training transitions across image and language models.
Source: arXiv cs.LG
MLOps/Systems • Score 85
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
arXiv:2608.13043v1 Announce Type: new
Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising solution, existing policies rely on local similarity heuristics, which we identify as being significantly misaligned with final generation quality. This discrepancy stems from the non-uniform propagation and accumulation of errors along the denoising trajectory. To address this, we propose Global-Impact Cache (GCache). We first establish a rigorous theoretical characterization of the error propagation upper bound. Recognizing that this bound can be overly conservative for complex, highly non-convex diffusion models, we further reparameterize the propagation exponent with a Bernstein form and reformulate cache policy search as a bilevel optimization problem. In detail, GCache identifies an optimal reuse policy in the inner objective while aligning the error-weighting function with generation quality loss in the outer objective. This framework effectively reconciles theoretical rigor with empirical performance, learning to prioritize computation where it most impacts visual fidelity. Extensive experiments demonstrate that GCache consistently outperforms prior caching strategies on both video and image generation. Notably, on the state-of-the-art Wan2.1 video diffusion model, GCache maintains a 2.17x speedup while significantly enhancing generation quality, reducing LPIPS from 0.1095 to 0.0316.
Source: arXiv cs.AI
NLP/LLMs • Score 85
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
arXiv:2608.12720v1 Announce Type: new
Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components. This static approach limits performance on heterogeneous memory queries, which often demand diverse evidence construction strategies. To address this, we introduce \textbf{ERSkill}, a retrieval-centric framework for self-evolving, skill-guided memory access. ERSkill compiles interaction histories into a structured memory store and represents retrieval behaviors as executable skills composed of fundamental primitives. At inference time, a trained router dynamically matches each query to the optimal skill to construct tailored evidence for answer generation. To enable continuous improvement, ERSkill co-evolves the skill set and the router during training. It employs an experience trie to efficiently record explored retrieval paths, alongside a double-frontier mechanism that safely decouples the expansion of new skill capabilities from stable, router-facing deployment. Experiments across multiple agent memory benchmarks demonstrate that ERSkill substantially outperforms strong non-evolving and self-evolving baselines. Notably, it improves the overall average across F1, BLEU-1, and LLM-judge scores by 31.3\% with Qwen3-Next-80B-A3B-Instruct and by 28.1\% with GPT-5.4-nano.
Source: arXiv cs.CL
NLP/LLMs • Score 85
Trie Automata for Constrained Decoding over Large Finite Sets
arXiv:2608.12574v1 Announce Type: new
Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of valid strings. Current constrained decoding systems handle this through general-purpose grammar compilation, which becomes prohibitively slow as the number of valid values grows into the thousands, a cardinality wall. We introduce the trie automaton, a specialized mechanism that exploits finite-set structure (shared prefixes, bounded depth, known cardinality) via Aho-Corasick multi-pattern matching to precompute per-node token masks. The trie achieves 7X faster per-step valid-token computation (0.65 us vs. 5.8 us) compared to XGrammar, one of the primary backends in vLLM and SGLang, and 2--6.5X faster compilation at K >= 300. Because precomputed masks enable a stateless serving path that bypasses the guided decoding pipeline, this advantage compounds in batch serving: end-to-end vLLM throughput reaches 219 req/s vs. XGrammar's 7.5 req/s at batch size 256 (29X). The 29X combines the algorithmic speedup with integration-path savings that only precomputed masks can unlock. Across seven tokenizer families (32K--262K vocabulary), the trie maintains sub-100ms compilation up to K = 10,000 and flat per-step cost regardless of set size, while guaranteeing 100% output validity.
Source: arXiv cs.AI
MLOps/Systems • Score 85
Harmonizing Safety and Speed: A Human-Algorithm Approach to Enhance the FDA's Medical Device Clearance Policy
arXiv:2407.11823v4 Announce Type: replace-cross
Abstract: The United States Food and Drug Administration's (FDA's) 510(k) pathway allows manufacturers to gain medical device approval by demonstrating substantial equivalence to a legally marketed device. However, the inherent ambiguity of this regulatory procedure has been associated with high recall among many devices cleared through this pathway, raising significant safety concerns. In this paper, we develop a combined human-algorithm approach to assist the FDA in improving its 510(k) medical device clearance process by reducing recall risk and regulatory workload. We first develop machine learning methods to estimate the risk of recall of 510(k) medical devices based on the information available at the time of submission. We then propose a data-driven clearance policy that recommends acceptance, rejection, or deferral to FDA's committees for in-depth evaluation. We conduct an empirical study using a unique dataset of over 31,000 submissions that we assembled based on data sources from the FDA and Centers for Medicare and Medicaid Service (CMS). Compared to the FDA's current practice, which has a recall rate of 10.3% and a normalized workload measure of 100%, a conservative evaluation of our policy shows a 32.9% improvement in the recall rate and a 40.5% reduction in the workload. Our analyses further suggest annual cost savings of approximately $1.7 billion for the healthcare system driven by avoided replacement costs, which is equivalent to 1.1% of the entire United States annual medical device expenditure. Our findings highlight the value of a holistic and data-driven approach to improve the FDA's current 510(k) pathway.
Source: arXiv stat.ML
MLOps/Systems • Score 85
Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping
arXiv:2608.12663v1 Announce Type: cross
Abstract: Wildfire susceptibility mapping typically relies on physical variables assembled from multiple remote-sensing, climate, and geospatial products. AlphaEarth Foundations (AEF) provides analysis-ready geospatial embeddings that may reduce this dependence on heavy harmonisation and task-specific feature engineering, but their value for wildfire susceptibility mapping has not been systematically evaluated. Using Victoria, Australia (2017-2025), as a case study, we show that AEF embeddings can reconstruct commonly used variables in wildfire susceptibility analysis with high accuracy. In downstream susceptibility models trained on satellite-derived fire occurrence data, embedding-based susceptibility models achieve ROC-AUC values above 0.92 and consistently identify high wildfire susceptibility across eastern Victoria, particularly Gippsland and the north-eastern uplands, with additional localized hotspots in central and northwestern Victoria. A key feature of AEF embeddings is their strong near-region transferability within climatically similar regions. When embedding-based models trained in Victoria are applied to Canberra and Western Sydney-Blue Mountains, ROC-AUC improves by around 4% at Canberra and declines by around 2% at Western Sydney-Blue Mountains, compared with a mean decrease of approximately 25% for physical-variable models. These findings provide practical guidance for using AEF embeddings and lay a foundation for scalable wildfire susceptibility mapping workflows for downstream users such as government agencies and (re)insurers.
Source: arXiv stat.ML
Theory/Optimization • Score 85
Federated Compositional Muon Optimizer for Matrix-Wise Models
arXiv:2608.12710v1 Announce Type: new
Abstract: Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these methods are still not particularly well-suited for hierarchical structured problems. To fill this gap, we propose an effective federated compositional Muon (FedCoMuon) optimizer to solve distributed matrix-wise compositional optimization problems. Specifically, our FedCoMuon optimizer builds on compositional gradient tracking and orthogonalized momentum. Moreover, we propose a variance reduced variant of FedCoMuon (FedCoMuon-VR) based on a momentum-based variance reduced technique. In theory, we analyze the convergence properties of our algorithms under the non-i.i.d. and non-convex settings. In particular, we prove that our FedCoMuon-VR obtains a lower sample complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution than the existing FedMuon algorithms. Extensive numerical experiments on robust federated learning and task-distributed risk-sensitive meta learning show that our proposed methods are competitive with existing compositional baselines and achieve the best reported accuracy in several settings.
Source: arXiv cs.LG
RecSys • Score 85
Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection
arXiv:2608.12573v1 Announce Type: new
Abstract: Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning workloads, including sparse activations and attention pruning. As data sizes grow, existing approaches become inefficient: exact methods incur high memory and compute overhead, while approximate methods often rely on brittle heuristics that degrade under adversarial or heavy-tailed inputs. In this paper, we introduce Prof-K, a fast, scalable, and distribution-agnostic top-k algorithm with probabilistic correctness guarantees. Prof-K performs a single-pass filtering procedure: a small random sample estimates an adaptive threshold, the N input elements are streamed once into a compact buffer, and an exact top-k routine on this buffer recovers the true top-k elements with probability at least 1 - $\epsilon$, where $\epsilon$ > 0 is user specified. We derive high-probability guarantees for correctness and buffer size, together with an approximately optimal sample size that minimizes overhead as a function of N and k. Empirically, Prof-K achieves 1.5x-10x speedups over the highly optimized PyTorch topk and recent RadiK implementations, with the largest gains in the large-scale, small-to-moderate-k regime where prior methods struggle most. Unlike previous approaches, these guarantees hold independently of the input distribution, ensuring robustness to adversarial settings. By relaxing the recall target (e.g., recovering 95% of the true top-k values), Prof-K additionally provides a principled accuracy-speed trade-off. We further demonstrate its impact on training BatchTopK Sparse Autoencoders (SAEs), where top-k selection constitutes a significant portion of the training cost.
Source: arXiv cs.LG
Theory/Optimization • Score 85
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
arXiv:2608.12925v1 Announce Type: new
Abstract: Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}$nspired $\textbf{M}$omentum (AIM) framework based on residual-penalty variable splitting, which interprets momentum as a multiplier-like correction driven by the splitting residual. AIM recovers the exponential moving average of gradients from an ADMM-style multiplier update and separates two mechanisms that are usually intertwined in practical optimizers: the residual penalty determines the update geometry, whereas the approximation of the objective-related subproblem determines the acceleration form. Building on AIM, we propose $\textbf{R}$elativistic $\textbf{A}$daptive gradient $\textbf{D}$escent with $\textbf{A}$ccelerated $\textbf{R}$esidual (RADAR), which combines relativistic adaptive geometry, decoupled residual correction, and second-order momentum filtering to improve the update direction and momentum estimation. We establish stochastic convergence through a variance-perturbed Lyapunov drift analysis. Experiments on supervised vision learning, language modeling, and reinforcement learning show that RADAR achieves consistent improvements over strong adaptive optimizer baselines.
Source: arXiv cs.LG
NLP/LLMs • Score 85
Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy
arXiv:2608.12674v1 Announce Type: new
Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions of active items, manual governance of price relationships is infeasible. Inconsistent pricing across item variants distorts customer value perception and cannibalizes sales. To address this, we present a scalable, context-aware Multi-Agent Framework designed to automate the construction of "Lines and Ladders" pricing taxonomies. Our framework employs specialized LLM agents to construct these coherent pricing structures by identifying key attributes, extracting multi-modal values, and applying hierarchical grouping logic. Evaluated on real-world enterprise data and deployed in production, our 3-Agent system achieves an F1-score of 0.83 for Lines, outperforming single-agent baselines by mitigating cognitive overload. The system achieves >90% precision and >75% recall in Food & Consumables, and 80.2% assignment accuracy in the unstructured General Merchandise catalog.
Source: arXiv cs.AI
NLP/LLMs • Score 85
MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents
arXiv:2608.12428v1 Announce Type: new
Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure. MindMemOS supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution. Its MindMemEvolve algorithm employs validation-driven evolutionary search to optimize memory schemas for target scenarios, whiledreaming consolidates accumulated memories by merging redundant records and resolving conflicts. In addition, implicit corrective feedback serves as a human-in-the-loop signal for identifying and revising potentially inaccurate or misaligned memories. Its MindSkillEvolve algorithm further transforms agent execution trajectories into reusable and progressively refined skills. MindMemOS achieves 94.03% accuracy on LOCOMO and 70.63% on PersonaMem. MindSkillEvolve improves SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline.
Source: arXiv cs.AI
MLOps/Systems • Score 85
A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family
arXiv:2608.12700v1 Announce Type: new
Abstract: Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept it if the output is close to a reference. A kernel can pass that test and still be silently wrong. It can return an ordinary number where the true answer is a NaN or an infinity, differ from run to run, break when the shape changes, or accumulate in fp16 where the reference keeps an fp32 total. We build the instrument that checks correctness properly: a contract-grade verifier of twelve adversarial gates, each a property a correct kernel must satisfy, several of them tolerance-free, so no choice of threshold can explain a failure away. Aimed outward, the verifier audits 2,638 machine-generated kernels that a public system's own harness had already accepted as correct. It finds 39.5% broken beyond any tolerance argument and 62.1% carrying at least one violation. The field's standard test accepts 1,487 kernels the verifier rejects, against only 14 the other way. We defend the finding four independent ways: a 7/7 positive control, a threshold-calibration sweep, 98.5% agreement with the reference benchmark's own correctness code, and a stratified hand-audit. Aimed inward, the verifier judges a kernel of our own: the first native Blackwell tcgen05 training backward for the gated-linear-recurrence (GDN) family, including the reverse-state stage the field still runs on a fallback. We establish its correctness independently, against a double-precision oracle, and train five family members through it. The correctness signal behind reported progress in kernel generation is far weaker than the numbers suggest, and a set of tolerance-free contracts would close most of the gap.
Source: arXiv cs.LG
NLP/LLMs • Score 85
CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility
arXiv:2608.12805v1 Announce Type: new
Abstract: Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification. Synthetic data promises a practical alternative: it can preserve useful statistical and clinical structure while reducing exposure of sensitive patient records. Prior studies often evaluate a single generator, one dataset, or a narrow downstream task, making it difficult to know when synthetic data can support model development and when it fails to preserve task-critical signal. We introduce CoMedBench, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets. In total the benchmark spans 37 dataset-task pairs across two modalities consists of 20 static tabular and 17 temporal ICU time-series-drawn from seven public data sources: three intensive-care databases (MIMIC-III, MIMIC-IV, and eICU) together with the UCI Machine Learning Repository, the CDC BRFSS diabetes cohort (2015), NHANES (1999-2014), and the pycox survival datasets (GBSG and METABRIC). The benchmark evaluates both statistical fidelity and task utility by comparing models trained and tested across real and synthetic data. In these settings, synthetic training data preserves most of the downstream signal: on tabular tasks the reference generator CoMed-CTGAN retains a mean AUROC utility (the synthetic-to-real performance ratio) of 90.6%, rising to 97.3% for the strongest generator, CoMed-TVAE. Temporal ICU tasks are harder and more generator-sensitive: CoMed-CTGAN retains 81.6% (AUROC) and only 64.0% under the imbalance-sensitive AUPRC, whereas CoMed-TVAE still retains ~95% (AUROC).
Source: arXiv cs.LG
NLP/LLMs • Score 85
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
arXiv:2608.12371v1 Announce Type: new
Abstract: Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper proposes \emph{MAS-DecStream}, whose main contribution is \emph{LLM-MR-CNP}: an extension of the classical Contract Net Protocol with semantic CFP formulation, progressive context disclosure, multi-round proposal revision, negotiation memory, and deterministic validation. Edge-cluster agents refine natural-language offloading proposals from local observations, predicted resource states, and qualitative runtime context, while hard resource and QoS constraints remain deterministic. Experiments derived from the Alibaba ASI Trace evaluate the extension at three levels: single- versus multi-round CNP, rule-based versus LLM-assisted refinement, and fixed-model single- versus multi-round negotiation. Under the evaluated configurations, MAS-DecStream reduces latency violations to 3\%, eliminates resource overcommitment, reaches a conflict-resolution rate of 0.91 with 20 agents, and improves utility by up to 22\% over the multi-round rule-based baseline. A separate 25-case evaluation shows model- and prompt-dependent accuracy--cost trade-offs. The results provide initial evidence that multi-round CNP refinement is the principal protocol-level gain, with LLM assistance adding value for qualitative and uncertain runtime context.
Source: arXiv cs.AI
MLOps/Systems • Score 85
Multi-perspective Imbalance-Conscious 6G Beamforming Optimization and Performance
arXiv:2608.12929v1 Announce Type: new
Abstract: The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches. We compared the predictive power of network, environmental, device, and vision feature groups for 6GBO. Additionally, it addressed other unsupervised perspectives that can enhance 6GBO, including clustering network scenarios using methods such as K-means, DBSCAN, and hierarchical clustering. Several imbalance-aware experiments revealed that network features possess better prediction power than device, environmental, and vision feature groups, as evidenced by their recall, F1-score and ROC-AUC values. For unsupervised ML exploration (assessed using Elbow, Silhouette score, and Davies-Bouldin Index methods), the results indicate that the deployment environment and type of device primarily influence clustering, rather than mobility-based attributes. Furthermore, the explainability analysis showed that bandwidth, IoT sensors, and mobility possess higher global feature importance across the feature groups. In the future, we would apply deep and reinforcement learning techniques to predict throughput/latency or to optimize rewards determined by performance indicators like SNR enhancement
Source: arXiv cs.LG
RecSys • Score 85
Diffusion-Based Data-Driven Assortment Optimization
arXiv:2608.11419v1 Announce Type: new
Abstract: Assortment optimization is a fundamental problem in revenue management, typically addressed using parametric choice models such as the multinomial logit (MNL) and its variants. While these models enable tractable formulations, their performance is sensitive to model misspecification and often struggles to capture complex customer behavior. In this paper, we propose a model-agnostic framework for assortment optimization based on guided discrete diffusion. We represent assortments as binary vectors and perform stochastic search via a learned reverse diffusion process, avoiding explicit combinatorial enumeration. To incorporate decision objectives, we introduce a reward-guided mechanism that biases local transitions using estimates of expected revenue. This allows the method to effectively balance exploration and exploitation during generation. Empirically, we show that the proposed approach consistently identifies high-quality assortments and remains robust under model misspecification, often recovering near-optimal solutions in high-dimensional settings. Moreover, the generative nature of diffusion enables the production of diverse high-performing assortments, offering flexibility beyond a single deterministic solution. These results highlight the potential of generative modeling as a scalable and robust paradigm for combinatorial optimization in data-driven decision-making.
Source: arXiv cs.LG
NLP/LLMs • Score 85
A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization
arXiv:2608.11483v1 Announce Type: new
Abstract: Hit-to-lead optimization requires iterative design of hit analogs across competing potency, selectivity, physicochemical, pharmacokinetic, safety, and synthetic constraints. We present SABLE (Synthetically-accessible Agentic Bayesian Ligand Exploration), an open-source framework that employs natural-language orchestration to guide chemical structure optimization. SABLE uses an LLM to interpret user-defined goals and route tasks, while specialized tools perform reaction-templated analog enumeration, physicochemical and ADMET property prediction, structure-based affinity scoring, and Bayesian optimization. The resulting workflow is a computational twin of the analytical and prioritization stages of the design-make-test-analyze cycle, providing provenance of each numerical output. Across single, and multi-objective optimization studies, SABLE enriches candidate sets for user-defined computational objectives while evaluating only a subset of the enumerated search space. Its modular architecture allows tools and characterization backends to be replaced by editing a simple config file, without modifying operational logic. SABLE provides an extensible decision-support framework for prioritizing synthetically constrained analogs in early-stage drug discovery.
Source: arXiv cs.AI
MLOps/Systems • Score 85
Market-Information-Aware Gated-LoRA of Foundation Models for Transferable Day-Ahead Electricity Price Forecasting
arXiv:2608.11359v1 Announce Type: new
Abstract: Electricity price forecasting is crucial for market participants but remains difficult because prices are volatile, market-specific, and closely tied to anticipated system conditions. Existing supervised methods depend largely on market-specific historical data, limiting their use in newly established or data-scarce markets. This paper proposes a market-information-aware adaptation framework that transfers the Chronos-2 time-series foundation model to day-ahead electricity price forecasting. It first constructs a multi-source market information (MSMI) interface aligning 7-day price context with pre-clearing supply--demand, reserve, maintenance, generator-capacity, and intertie variables, and then trains a source-domain gated low-rank adapter (LoRA), updating about $1\%$ of model parameters without target-market labels. The gate scales the frozen source adapter according to reserve-tightness and operating-state signals. A leave-one-market-out protocol is adopted for evaluating cross-market transferability. Experiments on four Chinese provincial day-ahead spot markets show that the proposed framework reduces the average MAE/RMSE by $6.24\%/7.99\%$ relative to market-information-aware zero-shot Chronos-2 and by $3.05\%/3.52\%$ relative to vanilla Source-LoRA. Experiments show that the gain is not reproduced by a learned global scalar or by random gate initialization, while the additional improvement over Source-LoRA is limited. These results suggest that market-structured inputs and state-dependent gated LoRA can provide a practical transfer path for data-scarce electricity markets.
Source: arXiv cs.LG
NLP/LLMs • Score 85
Lifecycle-Optimal Tokenization: Vocabulary Size as a Deployment-Regime-Dependent Infrastructure Parameter
arXiv:2608.11361v1 Announce Type: new
Abstract: Tokenizer vocabulary size is a foundational design choice in large language model (LLM) infrastructure, yet it is typically fixed at training time based on convention rather than deployment analysis. We show that the cost-optimal vocabulary is not a constant but a function of the serving regime. We formalize total deployment cost as $C_{lifecycle}(V) = C_{train}(V) + \lambda \cdot C_{infer}(V, B)$, where $\lambda$ is inference volume and $B$ is the serving batch size. Through controlled experiments on two GPU families spanning the memory-bound to compute-bound regimes (A10G, ridge $\approx$ 117 FLOP/byte; A100, ridge $\approx$ 183 FLOP/byte), we demonstrate: (1) the inference-optimal vocabulary shifts 16x with serving batch, from 32k at $B=1$ to 524k at $B=64+$, driven by amortization of the $V \times d$ unembedding matrix read; (2) at 1.3-2.3B model scale, quality (bits per byte, BPB) is optimized at $V=65$k, confirming scale-dependent vocabulary preference; (3) the lifecycle-optimal vocabulary diverges from training-optimal by up to 16x for production deployments. Quality is approximately invariant across the optimal range ($<$2% BPB spread), making vocabulary a pure systems optimization with no quality penalty in the measured range. Our results provide actionable capacity planning guidance: on-device deployments ($B=1$) should use $V \approx 32$k; datacenter serving ($B \geq 64$, $\lambda \geq 10$) should use $V \approx 131$-262k.
Source: arXiv cs.LG
Privacy/Security/Fairness • Score 85
Defending against Model Extraction for GNNs with Model Reprogramming
arXiv:2608.11495v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS). Still, their black-box deployment exposes them to Model Extraction (ME) attacks, in which adversaries steal intellectual property by querying APIs. Existing defenses suffer from a critical ''Euclidean bias'': they transfer image-based strategies (e.g., random noise) to graphs, ignoring the complex topological dependencies between nodes, which often results in severe utility degradation. Passive methods like watermarking also fail to prevent theft in real time. To bridge this gap, we propose GraphRP (Graph Reprogramming Protection), a proactive defense framework that repurposes Model Reprogramming for security. Unlike static perturbations, GraphRP introduces a Structure-Aware Gating Mechanism driven by learnable topological prototypes. This creates a dynamic ''structural firewall'' that selectively modulates the model's decision boundary: it preserves fidelity for benign queries residing on the training manifold, while maximizing the Fisher Information along the perturbation direction for adversarial queries. Under standard assumptions (bounded loss, optimal attacker, and local second-order approximation), we prove a lower bound on the attacker's estimation error that increases with the structural sensitivity of the reprogramming noise. Extensive experiments on both hard-label and soft-label ME attacks demonstrate that GraphRP significantly degrades attack effectiveness while preserving benign utility.
Source: arXiv cs.LG
Theory/Optimization • Score 85
Variational Parameter Calibration with Physics-Aware Latent-Space Surrogates
arXiv:2608.11435v1 Announce Type: new
Abstract: Forward and inverse modeling of parametric dynamical systems requires surrogate models that are not only accurate for state prediction, but also informative for parameter calibration. However, a systematic end-to-end differentiable formulation for coupling deep-learning-based reduced-order surrogates with variational parameter estimation remains underdeveloped. In this work, we introduce a physics-aware neural-network-based latent-space framework for reduced-order forward modeling and variational parameter estimation. The proposed autoencoder-based approach yields a differentiable surrogate that maps physical parameters to predicted flow fields through a latent representation. The observable supervision is used during offline training to encourage the latent variables to retain information correlated with system parameters, while the online inverse problem is solved in the parameter space through the surrogate-induced observation operator. The method is evaluated on two computational-fluid-dynamics benchmarks. The results show that reconstruction accuracy alone is insufficient for inverse modeling, owing to the lack of end-to-end differentiability or physics awareness for variational parameter calibration. Quantitative latent-space analysis further shows that observable supervision improves case-level separability and temporal organization of latent representations. Experiments with realistic measurement settings, including noisy, low-resolution, randomly masked, and block-wise partial observations, demonstrate the robustness of the proposed framework and show that it generally reduces calibration error and variability compared with the standard surrogate models.
Source: arXiv cs.LG
Vision • Score 85
Test-Time Hallucination Control in Large Vision-Language Models
arXiv:2608.11474v1 Announce Type: new
Abstract: Object Hallucination in large vision-language models (LVLMs), where models generate non-factual content about input images, remains a critical barrier to their reliability in real-world applications. Existing mitigation strategies can be categorized into training-based and training-free methods. Training-based methods often achieve strong performance but are costly, requiring extensive computational resources, large-scale data, and time-consuming fine-tuning. Training-free approaches are particularly appealing due to their efficiency. However, existing training-free methods either require multiple decoding rounds, which adds computational overhead, or modify internal states in a model-specific way that risks degrading pretrained knowledge. We propose Test-Time Hallucination Mitigation (TTH) method, a novel training-free method that addresses both limitations. TTH introduces a token-validator module, implemented as a zero-shot Multi-Modal Classifier (MMC), to generate auxiliary logits grounded in the input image. These logits are fused with the original LVLM outputs at the token level for object tokens selected from a candidate pool. An entropy-based weighting scheme is then applied to enable robust and accurate predictions. Extensive experiments across multiple LVLM families and diverse benchmarks demonstrate that TTH consistently improves accuracy and robustness, underscoring its generalizability and practical effectiveness. Code is released at https://github.com/Mehran-TAM/TTH
Source: arXiv cs.CV
Vision • Score 85
Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision
arXiv:2608.11564v1 Announce Type: new
Abstract: Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent studies have sought to transfer knowledge from RGB-based foundation models to thermal modalities, yet the rich hierarchical representations these models encode remain underutilized. To address this limitation, we propose RGB-HS, a novel framework for thermal-image depth estimation that leverages hierarchical supervision from an RGB-based foundation model. Specifically, we first replace the baseline thermal encoder with a foundational model and introduce a parallel RGB branch that also employs a foundational model as an encoder of the same architecture, taking RGB images as input. The alignment is then performed across multiple levels between the tokens of the two encoders, allowing the thermal student branch to capture both structural precision and semantic abstraction from the RGB teacher branch. Furthermore, we introduce verification to refine the alignment process by weighting tokens from the RGB branch based on RGB image quality. Extensive experiments on the popular benchmark demonstrate that RGB-HS achieves competitive performance and more effectively exploits the representational capacity of RGB-based foundation models for depth estimation on thermal images.
Source: arXiv cs.CV
RecSys • Score 85
From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation
arXiv:2608.11493v1 Announce Type: new
Abstract: Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large Language Models (LLMs) offer a promising alternative by predicting user engagement directly from raw text logs, empirical analysis in this study identifies a critical failure mode termed bidirectional rationalization. In a zero-shot setting, LLMs are found to convincingly argue for both positive and negative user engagement outcomes on the exact same item with identical evidence, highlighting the unreliability of off-the-shelf LLMs in predicting user engagement. To resolve this, we develop and apply a sequential behavioral alignment framework pairing fine-tuning with preference optimization over paired correct and counterfactual rationales. Evaluated on real-world homepage interaction logs, this aligned reasoning approach achieves a 32.19\% lift in Macro-F1 score over the zero-shot baseline and matches the production feature-engineered baseline. The results demonstrate that behavioral alignment mitigates bidirectional rationalization while delivering human-interpretable reasoning traces without manual pipeline overhead.
Source: arXiv cs.AI
NLP/LLMs • Score 85
Foresight Without Seeing: Latent Futures for World Action Models
arXiv:2608.11605v1 Announce Type: new
Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction. Existing WAMs differ in how predictive dynamics are exposed to the action pathway. Explicit-future WAMs provide direct access to predicted scene evolution, but incur substantial inference costs from iterative video denoising. In contrast, direct-policy WAMs efficiently predict actions from the current observation but lack an explicit inference-time interface for exposing predictive dynamics to the Action DiT. To bridge this gap, we propose ForeWAM, a dynamics-conditioned direct-policy WAM that provides predictive context for action generation without decoding future videos. At its core, Future-KV performs a single Video DiT prefill over the current visual latent and stochastic future slots, and reuses the resulting layer-wise key-value states throughout action denoising. We further introduce dynamics registers supervised by a frozen latent action teacher, encouraging the implicit future states to capture interaction-induced transitions such as object motion, contact changes, and task progress. Ground-truth future observations and the teacher are used only during training; deployment requires neither and performs no future video generation. Without embodied robot data pretraining, the standard and accelerated variants of ForeWAM achieve average success rates of 96.7% and 96.9% on LIBERO, respectively. The standard variant further achieves 61.6% success on LIBERO-Plus. These results demonstrate that direct-policy WAMs can retain efficient action prediction while exposing predictive dynamics to the action pathway without explicitly generating future observations.
Source: arXiv cs.AI
NLP/LLMs • Score 85
AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search
arXiv:2608.11250v1 Announce Type: new
Abstract: Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission.
Source: arXiv cs.AI
NLP/LLMs • Score 85
QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving
arXiv:2608.12121v1 Announce Type: new
Abstract: Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent Caching (PIC) mitigates it by reusing precomputed Key-Value (KV) across positions, but its efficiency is constrained by the large volume of text tokens. Rendering text chunks as images can compress the text into fewer visual tokens, but the rendered-image PIC suffers more severe quality degradation than the text PIC. This representation-specific gap primarily arises from contextual mismatches across independently compiled caches and the loss of fine-grained textual evidence during visual compression. Existing PIC repair methods mainly address the former through selective recomputation, but they incur online computation and cannot recover lost textual details. We propose QV-PIC, a query-aware dual-resolution PIC reuse framework guided by model-native templates. Offline, QV-PIC compiles visual caches under the model's native chat-template prefix, improving PIC quality without online recomputation. Online, it preserves global context with low resolution and restores fine-grained textual evidence within a high-resolution budget by cumulative query relevance scores, retaining the efficiency benefit of visual compression. Across six tasks, QV-PIC improves average F1 by 21.6 points over vanilla rendered-image PIC, closes the gap to vanilla text PIC, and surpasses optimized text PIC by 2.58 F1 while reducing TTFT by 17.2\%. Relative to full prefill, it cuts TTFT by 83.8%.
Source: arXiv cs.CL
NLP/LLMs • Score 92
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
arXiv:2608.11742v1 Announce Type: new
Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committing a mid-entropy pivot position can induce a pronounced reduction in uncertainty across the remaining masked positions. This uncertainty reduction allows subsequent steps to unmask more tokens in parallel, thereby accelerating the overall decoding process. To exploit the ripple effect, we propose Ripple-Pivot Search (RPS), a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode). Across 3 dLLMs and 4 reasoning and code-generation benchmarks, RPS achieves 4-10$\times$ wall-clock speedup over the standard decoder while preserving generation quality, and improves accuracy over the previous lookahead baseline by up to 5.49% while delivering higher throughput in most settings. When integrated with KV caching, RPS further achieves up to 18$\times$ wall-clock speedup over the standard decoder.
Source: arXiv cs.CL
NLP/LLMs • Score 85
Total Recall at What Cost? Benchmarking the Serving Cost of Agentic Memory Systems
arXiv:2608.11879v1 Announce Type: new
Abstract: Long-running conversational agents increasingly rely on a memory system to avoid resending the whole conversation each turn, yet how much that costs to serve has received little systematic benchmarking. We compare three memory systems (Mem0, Hindsight, and Mastra Observational Memory) against two reference strategies -- a fixed-size rolling window and resubmitting the full transcript -- across two backbones and conversations of up to 400 turns, pairing every cost measurement with answer accuracy on 665 LoCoMo questions. First, a memory system's serving cost cannot be predicted from conversation length and message size alone: a regression that tracks the two reference strategies closely misses the memory systems by 18-69%, their cost driven instead by internal memory behavior. Second, a break-even analysis shows that whether -- and when -- a memory system becomes cheaper to serve than the full transcript is highly sensitive to the system and the backbone, from the first tens of turns for the cheapest to never within 400 turns for the most expensive. Third, no system wins on both axes: accuracy spans 21-54%, and the backbone choice drives cost as much as the memory system does.
Source: arXiv cs.CL
MLOps/Systems • Score 85
LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training
arXiv:2608.11919v1 Announce Type: new
Abstract: Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage bandwidth. Existing offloading systems reduce GPU residency, and MegaTrain shows that a CPU-master layer-streaming executor can train large models on a single GPU, but fixed checkpointing and placement heuristics still leave communication exposed on the critical path. We propose LazyTrain, an optimization layer over a layer-streaming executor. LazyTrain formulates checkpoint selection, activation placement, recomputation, and CPU-GPU-NVMe communication overlap as a mixed-integer scheduling problem, then executes the solved policy during training. It further couples 8-bit optimizer states with fast gradient clipping as a single Hybrid 8-bit operator: state compression reduces optimizer-state memory, while fast clipping counteracts the additional CPU-side update overhead. Across H800 experiments from Qwen2.5-3B to Qwen3.6-27B, LazyTrain improves sustained TFLOPS over matched baselines runs by approximately 1.24$\times$; RTX 3090 experiments likewise increase the maximum feasible batch size by one at each model scale. In the primary Qwen3.6-27B H800 MetaMathQA run, LazyTrain reaches 219.95 TFLOPS and 1361 tokens/s at batch size 72, peaks at 68.84\,GB of GPU memory, and obtains 95.42\% exact-match accuracy on the full evaluation split. The source code is available at https://github.com/DataArcTech/LazyTrain.
Source: arXiv cs.CL
RL • Score 85
Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings
arXiv:2608.11324v1 Announce Type: new
Abstract: This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical, water-cooled chiller plant and its associated air side. Rather than converging to a single scalarised policy, the controller maintains a product archive of specialised policies indexed jointly by a data- driven operating context, a cluster of daily weather and load regime, and a context-invariant behaviour descriptor, filled by a gradient-free evolutionary operator and a soft-actor-critic policy-gradient operator that share one replay buffer. Every action is filtered through a deterministic safety shield before execution. The controller is trained on a two-tier reduced-order environment representing the latent load, cooling-tower approach and humidity constraints of a Singapore commercial building, and is evaluated over a full annual backtest against an ASHRAE Guideline 36 baseline.
Source: arXiv cs.LG
RL • Score 85
Self-Evolving Embodied Agents via Skill-Harness Evolution
arXiv:2608.11350v1 Announce Type: new
Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable robot APIs that may be unavailable in fixed-interface settings. We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts. In SHAPER, the same frozen model can serve as both planner and optimizer, refining its external skills and context-code harness without parameter updates. We evaluate SHAPER on VLABench and ESI-Bench, covering embodied agents with different low-level action interfaces, and compare against pure execution, supervised fine-tuning, and test-time-scaling baselines such as verifier-free selection and voting. Our results suggest that skill-and-harness optimization is a practical route to self-evolving embodied agents when model training is expensive, unavailable, or undesirable.
Source: arXiv cs.CL
NLP/LLMs • Score 85
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
arXiv:2608.11338v1 Announce Type: new
Abstract: Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiveness. As a result, little is known about what skill learning strategies save cost. We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction. By executing sequences of actions deterministically, a program-augmented agent can reliably and cheaply achieve goals that would otherwise require trial and error and risk degenerate behavior over long horizons. An agent can learn at inference time by incrementally discovering these programs and equipping them for future tasks. We hypothesize that past trajectories contain enough signal to guide skill learning, even without replay or validation, provided the agent can learn to analyze them. To test our claims, we propose SpeedRunner, a coding agent that analyzes trajectories and refactors skills for better performance on future tasks. Across three different embodied environments, we show that SpeedRunner consistently achieves the frontier in learning and cost reduction while remaining robust against distribution shifts and environmental randomness.
Source: arXiv cs.CL
NLP/LLMs • Score 85
Towards the Harness of Embodied Agents
arXiv:2608.11246v1 Announce Type: new
Abstract: The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We present Thea, a harness in which an agentic loop orchestrates robot capabilities, each wrapped as a callable tool. It inherits the core components of coding agents, modified as the physical world requires. The world, however, withholds two abilities that software grants for free: reading the state of the world, and judging the outcome of an action. To bridge these gaps, Thea introduces Scene Graph as Context, a persistent, symbolic representation of the world, and Evaluation as Exit Codes, which detects when an action should terminate, judges whether it succeeded, and on failure diagnoses the cause. Together they close the loop between the agent and the physical world. Rich behaviors then emerge from the composition of tools, and the closed loop carries long-horizon tasks to completion in real environments.
Source: arXiv cs.AI
NLP/LLMs • Score 85
A Theoretical Framework for Modular Learning of Robust Generative Models
arXiv:2602.17554v3 Announce Type: replace-cross
Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly, combining small, domain-specific experts to match monolithic performance, and can we do so robustly for any data mixture, eliminating heuristic tuning? We present a theoretical framework for modular generative modeling where a set of pre-trained experts are combined via a gating mechanism. We define the space of normalized gating functions $\mathcal{G}_{1}$ and formulate the problem as a minimax game to find a single robust gate that minimizes divergence to the worst-case data mixture. We prove the existence of such a robust gate using Kakutani's fixed-point theorem and show that modularity acts as a strong regularizer, with generalization bounds scaling with the lightweight gate's complexity. Furthermore, we prove that this modular approach can theoretically outperform models retrained on aggregate data, with the gap characterized by the Jensen-Shannon Divergence. Finally, we introduce a scalable Stochastic Primal-Dual algorithm and a Structural Distillation method for efficient inference. Empirical results on synthetic and real-world datasets confirm that our modular architecture effectively mitigates gradient conflict and can robustly outperform monolithic baselines.
Source: arXiv stat.ML
NLP/LLMs • Score 85
Generative Video Compression Based on Hierarchical Referencing
arXiv:2608.11618v1 Announce Type: new
Abstract: Diffusion-based generative video compression has emerged as a promising paradigm to improve perceptual quality, where latent frames are required to be encoded efficiently while serving as denoising conditions. However, existing methods neither carefully design reference and quality structures during latent coding nor account for the impact of frame-level quality variation on denoising procedure, which limits coding efficiency and aggravates artifact propagation during generative reconstruction. In this paper, we propose GVCHR, Generative Video Compression based on Hierarchical Referencing. The key idea is to organize latent frames hierarchically, where the selected high-quality references benefit both latent coding and generative reconstruction. In latent coding, GVCHR couples a hierarchical reference structure with a hierarchical quality structure, assigning more bits to lower-layer frames that are reused more frequently as references. Built on this design, we introduce Hierarchical Temporal Context Mining to exploits complementary short- and long-term temporal context for effective latent coding. In generative reconstruction, the coding-side hierarchy is incorporated into a Hierarchical Attentive Adapter which is attached to a video diffusion transformer. This adapter uses hierarchical attention to restrict each latent frame to attend only to the same- or lower-layer references, thereby reducing artifact propagation during denoising. Experiments validate GVCHR on multiple benchmarks. Compared with the previous state-of-the-art method, GVCHR achieves 50.5% and 54.0% BD-rate gains in terms of LPIPS and DISTS, respectively, while also delivering clearly improved visual quality.
Source: arXiv cs.CV
MLOps/Systems • Score 85
Hierarchical Federated Transfer Learning in Digital Twin-Based Vehicular Networks
arXiv:2608.11532v1 Announce Type: new
Abstract: In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy. However, Federated learning struggles to adequately train a global model when confronted with data heterogeneity and data sparsity among vehicles, which ensure suboptimal accuracy in making precise predictions for different vehicle types. To address these challenges, this paper combines Federated Transfer Learning (FTL) to conduct vehicle clustering related to types of vehicles and proposes a novel Hierarchical Federated Transfer Learning (HFTL). We construct a framework for DT-VANET, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model. In addition, we developed a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles. Lastly, detailed experiments on real-world datasets are conducted, considering different performance metrics that verify the effectiveness and efficiency of our algorithm.
Source: arXiv cs.LG
MLOps/Systems • Score 85
Federated Learning for the Design of Parametric Insurance Indices under Heterogeneous Renewable Production Losses
arXiv:2601.12178v2 Announce Type: replace-cross
Abstract: We propose a federated learning framework for the calibration of parametric insurance indices under heterogeneous renewable energy production losses. Producers locally model their losses using Tweedie generalized linear models and private data, while a common index is learned through federated optimization without sharing raw observations. The approach accommodates heterogeneity in variance and link functions and directly minimizes a global deviance objective in a distributed setting. We establish theoretical guarantees under sub-exponential covariate distributions, showing that the Lipschitz constants of the local Tweedie objectives scale as $\frac{1}{\phi_i}$, where $\phi_i$ is the dispersion parameter of producer $i$. This heterogeneity in smoothness causes naive federated averaging to be biased toward producers with stable microclimates --- precisely those least in need of basis-risk protection --- and motivates the use of corrected aggregation schemes. We implement and compare FedAvg, FedProx and FedOpt, and benchmark them against an existing approximation-based aggregation method. A progressive pool expansion experiment involving up to 121 solar farms in Germany reveals that the approximation-based method becomes entirely non-computable beyond the pool of 50 farms, while federated learning remains valid and actively improves as the pool grows. Federated learning is also over $250\times$ faster than the approximation-based benchmark, establishing it as the only computationally and statistically valid approach for heterogeneous producer pools.
Source: arXiv stat.ML
MLOps/Systems • Score 85
Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
arXiv:2510.17543v3 Announce Type: replace-cross
Abstract: Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging. We study edge-cloud cascades that must preserve conditional coverage: whenever the edge returns a prediction set, it should contain the true label with a user-specified probability, as if produced by the cloud model. We formalize conditional coverage with respect to the cloud predictive distribution, and introduce a conformal alignment-based (CAb) cascading mechanism that certifies this property with user control over the risk level. Our method casts escalation from edge to cloud models as a multiple-hypothesis testing (MHT) problem, tailoring conformal alignment (CA) to select which inputs can be safely handled at the edge. The proposed CAb model cascading method yields statistical guarantees on the average fraction of edge decisions that satisfy cloud-level conditional coverage. The procedure applies to arbitrary edge prediction sets, including variants of conformal prediction (CP), and exposes a tunable trade-off among coverage, deferral rate, and set size. Experiments on CIFAR-100 image classification and the TeleQnA question-answering (QA) benchmark show that the proposed CAb cascade maintains the target conditional coverage for edge predictions while substantially reducing offloading to the cloud and incurring modest increases in prediction-set size.
Source: arXiv stat.ML
Theory/Optimization • Score 85
Heterogeneous transfer learning for high-dimensional regression with feature mismatch
arXiv:2412.18081v3 Announce Type: replace
Abstract: We study Heterogeneous Transfer Learning (HTL) for high-dimensional regression with differing feature sets. Such feature mismatch arises when some variables available in a data-rich source domain are unavailable in a data-poor target domain. Yet most homogeneous TL methods require the same feature space in both the source and target domains, limiting their practical applicability. Conversely, existing HTL methods lack statistical error guarantees, limiting their utility for scientific discovery. We propose an HTL method that first learns a feature map between the missing and observed features leveraging the vast source data, imputes the unavailable features in the target, and then performs a two-step TL for penalized regression. We consider both the linear and the nonparametric feature maps. We develop upper bounds on the estimation and prediction errors of HTL, assuming that the source and target parameters differ sparsely, without requiring the target model itself to be sparse. We also establish matching minimax lower bounds, showing that the proposed procedures achieve optimal rates. Our results elucidate the effects of model complexity, sample size, the quality and differences in feature maps, and differences in the models across domains. We also derive minimax rates for the misspecified homogeneous TL model that discards unavailable features and show that our HTL procedure can attain a smaller error rate than homogeneous TL. We further extend the framework to multiple source domains and develop a negative-transfer defense that provably excludes adversarial sources from transfer with high probability.
Source: arXiv stat.ML
NLP/LLMs • Score 85
CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
arXiv:2608.11588v1 Announce Type: new
Abstract: Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations. We introduce CoAdapt-GUI, a test-time adaptation (TTA) framework that jointly adapts structured workflow context and policy from the agent's own target-app rollouts and rewards. The workflow context retains transferable procedures, failure modes, and verification rules while excluding app-bound source details. This separation allows reusable workflow knowledge to guide adaptation without transferring source-interface state. For policy adaptation, task-context-matched group-relative optimization updates a LoRA adapter on a frozen vision-language model. Across two unseen-app evaluations, CoAdapt-GUI reaches 45.0% on AndroidWorld-Generalization, compared with 37.5% for the reported Policy-Only TTA baseline, and raises AndroidWorld Plus performance from 38.6% to 52.9%. These results show that transfer-constrained workflow context provides substantial gains and that joint policy adaptation further improves held-out performance.
Source: arXiv cs.AI
MLOps/Systems • Score 85
Transferable Above-Ground Biomass (AGB) Estimation Model from Multi-Sensor Data with Sparse Field Calibration
arXiv:2608.11638v1 Announce Type: new
Abstract: Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable. While field inventories provide high localized accuracy, they are spatially sparse; conversely, spaceborne LiDAR from the Global Ecosystem Dynamics Investigation (GEDI) offers broad biomass samples but lacks spatial continuity and systematic underestimation of high-biomass forests. This paper presents an operational framework centered on a single globally trained convolutional neural network (CNN) that is seamlessly adapted to each new landscape through a lightweight empirical field-calibration workflow. The global model combines optical (Sentinel-2), C-band SAR (Sentinel-1), L-band SAR (ALOS-2 PALSAR-2), and terrain (DEM) data. It is trained once against GEDI Level-4A biomass reference data spanning multiple regions and both wet and dry seasons so that it learns the persistent woody-structure rather than a single-date appearance. To avoid retraining for every landscape, the framework applies a small number of local field plots to fit a scale-and-bias correction that aligns the global prediction with ground truth in each region. The pipeline harmonizes sensor data onto a shared 10 m grid, derives vegetation indices and polarimetric ratios, computes per-band normalization stats, and trains the CNN with a hybrid log-domain SmoothL1 with RMSE loss for skewed biomass distribution. On held-out validation the global GEDI-based model achieved R^2 approximately 0.78 and RMSE approximately 22 Mg/ha. A subsequent field calibration combining Random Forest fine-tuning under a 10-fold cross-validation eliminates localized regional biases. This improves local validation performance to R^2 approximately 0.82 and reduces RMSE to approximately 15 Mg/ha, outperforming both the uncalibrated global model and the ESA CCI Biomass product against field plots.
Source: arXiv cs.LG
RL • Score 85
GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs
arXiv:2608.11674v1 Announce Type: new
Abstract: On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities, cross-task capability degradation, and response-length inflation. Although prior work has characterized the subspace geometry of aggregate updates, the stepwise variation of this geometry and its relationship to model performance remain unclear. We introduce Principal-Subspace Overlap, a dimension-corrected measure of individual rollout updates relative to the dominant singular subspaces of pretrained weights. Despite low average overlap, transient spikes often precede performance degradation. To address this, we propose GCPO (Geometrically Constrained Policy Optimization), which applies hard bilateral orthogonal projections to constrain updates to the complementary subspaces, preventing such excursions by construction. Across mathematical reasoning, code generation, and tool-use tasks on Qwen3-8B and GLM4-9B, GCPO consistently outperforms GRPO and recent variants, including DAPO and GSPO, improving over the base models and the strongest baseline by up to 27.69 and 2.37 points, respectively. Furthermore, GCPO preserves general capabilities, eliminates response-length inflation, and stabilizes policy entropy. Our findings provide a new diagnostic lens and a principled design perspective for stable reinforcement learning post-training.
Source: arXiv cs.LG
Vision • Score 85
Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines
arXiv:2608.11770v1 Announce Type: new
Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline.
Source: arXiv cs.CV
NLP/LLMs • Score 85
FLARE++: Low-rank attention with dynamic attention routing
arXiv:2608.11519v1 Announce Type: new
Abstract: Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems. Efficient latent-attention models such as the Fast Low-rank Attention Routing Engine (FLARE) avoid that cost by routing all N tokens through M << N learned latent queries, but those queries are parameters: once trained, the same learned query templates serve every input. We remove this restriction with FLARE++, a low-rank attention architecture with dynamic token routing. FLARE++ reuses FLARE's own encoder to build its routing queries: learned latent seeds drive one extra encode call that gathers the N input tokens into M input-conditioned queries, and those queries then determine how the same tokens are compressed and redistributed. This preserves FLARE's explicit low-rank factorization and linear O(NM) complexity, and expresses the complete routing operation with standard scaled dot-product attention (SDPA) calls alone. We also provide a multi-GPU context-parallel implementation that shards input tokens across devices without ever gathering the full token sequence on one of them. FLARE++ is competitive across a set of standard PDE surrogate benchmarks, improving on fixed-query FLARE by 24% on average, and it gains 2.3 points of average accuracy on Long Range Arena.
Source: arXiv cs.LG