overfeed.news
Anuncio

NexTalk

Automatiza la primera respuesta. Mantén el toque humano.

Chat en vivo con agentes de IA en tu modelo y tu clave de API, con traspaso a tu equipo.

Empezar gratis

Tema

LLMs

2972documentos

229últimos 7 días

arXiv AI Papers

Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning

Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by the ontological mismatch of applying continuous physical motion models to discrete logical behaviors. To address these limitations, we propose a novel framework that reformulates data association as a sequential decision-making task within a Markov Decision Process (MDP). We solve the defined MDP via Behavior Cloning (BC) to avoid complex reward engineering by directly learning from expert demonstrations. We instantiate the policy using two complementary architectures, including a lightweight Transformer that treats association as a multi-label classification task over linearized event histories, and a fine-tuned Large Language Model (LLM) that reformulates the problem as conditional text generation to leverage pre-trained semantic knowledge. Extensive evaluations on three diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, particularly in resolving concurrent multi-resident events. Furthermore, the LLM-based policy shows preliminary cross-environment transfer potential under benchmark settings, while its robustness in real deployments still requires further validation.

en
arXiv AI Papers

Robots in the City: Persona-Based Perceptions of Urban Robots

Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a street remains unclear. We examine how robot presence and type affect perceived safety across urban contexts. We generate 18 images of Seoul streets that vary in time of day, road class, and robot condition (no robot, a delivery robot, or a humanoid). Two multimodal large language models (MLLMs), Qwen3.8-27B and Gemma4-26B, each conditioned on 500 synthetic personas, choose the safer image in each pair, and 25 human respondents complete the same task. Both models prefer streets without robots and favor the delivery robot over the humanoid. Robots are chosen more often at night and less often by older personas, whereas road class has smaller effects. In the model rationales, the delivery robot appears as a physical obstacle, whereas the humanoid appears as either a threat or a source of protection. Like humans, both models chose robots more often at night, but chose the humanoid over the delivery robot far less often, and Gemma showed a night effect for the humanoid about three times that of humans. These results show that the effect of a robot on perceived safety depends on when it appears, and that persona-conditioned MLLMs capture only part of human judgments.

en
arXiv AI Papers

Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination

Graphs play an increasingly important role in large language model (LLM) systems, supporting structural reasoning, knowledge grounding, retrieval, and memory. As these systems evolve toward the agentic era, graphs also organize execution dependencies and multi-agent communication, linking intermediate observations and retained information to subsequent decisions. However, understanding their contribution requires distinguishing the function of each graph operation, the component responsible for its computation, and the subsequent use of its output. This survey introduces an operation-level role--locus taxonomy for reasoning, knowledge and evidence, retrieval and memory, execution, and coordination. We compare how graph observations and external computations guide decisions, how memory representations and updates support later tasks, and how dependencies constrain execution and information delivery. These comparisons distinguish improvements in local metrics from downstream task performance while retaining the conditions under which results were reported. We then organize benchmarks, comparison designs, process diagnostics, and system costs into an evaluation framework. Finally, we identify open challenges in adaptive computation and stopping, memory maintenance, and dependency-aware recovery. The survey provides a basis for assessing when graph mechanisms are useful and for evaluating their effects across components and stages.

en
arXiv AI Papers

Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

RL for LLM reasoning often reaches an early performance plateau as the policy distribution becomes increasingly sharp. Recent work has studied policy entropy as both a diagnostic and a control signal for this behavior. In our experiments, however, increasing entropy alone does not reliably change the eventual plateau. We analyze RL through its implicit target policy and derive a sharpness factor κ, together with an effective counterpart κ_{eff}, that describes how strongly reward or advantage gaps are translated into probability-ratio gaps. Motivated by this view, we introduce reward budgeting, a plug-in advantage construction that assigns a fixed total reward budget to each prompt. For binary rewards and independent on-policy rollouts, its unclipped score-function estimator follows the gradient of an exact finite-G concave objective with diminishing returns, while its advantage gap decreases as more rollouts become correct. For general rewards, a shifted log-mean interpretation holds asymptotically under the stated regularity conditions. These results motivate, rather than establish exact objective equivalence for, the clipped implementations. On Qwen3-8B and Llama3.2-3B-Instruct, reward budgeting consistently improves a range of RL baselines, with gains up to +12.50 on AMC23 and +10.00 on AIME24 and AIME25. Overall, our results support an update-dynamics view of premature convergence and show that strong gains can be obtained without explicitly preserving entropy.

en
arXiv AI Papers

Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models

Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory even though only a few experts are activated per token: they account for over 90% of model size in modern MoE-MLLMs (e.g., 54 GB out of about 58 GB in BF16 for InternVL3.5-30B-A3B and Qwen3-VL-30B-A3B). Expert pruning has emerged as an effective compression strategy, but existing methods aggregate importance uniformly across tokens, ignoring that the same expert may serve different roles for vision versus language processing. To address this, we propose MAEP (Modality-Aware Expert Pruning), a training-free framework that decomposes expert importance by modality in a single forward pass. MAEP introduces (1) Delta-H Output (ΔH), a redistribution-aware metric measuring the MoE output change when an expert is removed, and (2) low-attention vision tokens as a vision-side pruning signal that is dataset-stable: its expert-importance ranking remains stable across different datasets. Text-side importance serves as a preservation signal while vision-side importance serves as a pruning signal, and experts are ranked globally across layers. Experiments on three MoE-based MLLMs across multimodal and text benchmarks show that MAEP outperforms modality-agnostic baselines on the majority of multimodal benchmarks while remaining competitive on text-only tasks, reducing the BF16 expert weight footprint by about 27 GB (about 47% of total memory) so that the full weight footprint of an approximately 58 GB model fits within a single 40 GB GPU. Code is available at https://github.com/nota-github/MAEP.

en
arXiv AI Papers

Does Your Trial Simulator Know What the Drug Does? An Intervention-Blind Test of Interventional Validity on 7,207 Registered Trials

Patient world models are increasingly proposed as simulators of clinical trials, and recent surveys rank their capabilities on a ladder from temporal prediction to counterfactual rollouts. Position on that ladder is currently assigned by reading papers rather than by measurement. We turn the counterfactual rung into a measured quantity. From 30,119 completed phase 2/3 trials with results posted to ClinicalTrials.gov we construct 9,996 audited within-trial contrasts from 7,207 trials, and we score a simulator on how much of its accuracy depends on knowing which intervention was tested. The instrument is an intervention-blind reference: the same model, trained on the same trials, with every intervention-identifying field withheld. Interventional skill is the error the full model removes relative to that reference. On a temporal split (878 test contrasts from 655 trials) a registry-trained gradient-boosting simulator removes a fifth of the error of a trivial baseline, but its interventional skill is -0.12 (95% CI -0.21 to -0.05): withholding the intervention makes it better, and no alternative featurisation, stratum, temporal cut or same-molecule retrieval yields an interval above zero. A frontier language model reading only the registered protocol has interventional skill 0.20 [0.08, 0.31]; smaller and open-weight models sit at the limit of detection. Perturbation tests show the large model uses the intervention as such: swapping the arms reverses the sign of its prediction in 86% of contrasts. The blind reference is itself not drug-blind (a language model recovers the withheld drug class 45% of the time from the blind prompt), so interventional skill is a conservative lower bound. A reliability layer shows that ranking by predicted error lowers it but that calibrated error control does not transfer under temporal shift. Benchmark, code, prompts and per-call model outputs are released.

en
arXiv AI Papers

CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism

As sequence lengths continue to grow, distributed attention based on sequence parallel (e.g., Ring-Attention) has become a mainstream solution for large language models (LLMs). Nevertheless, inherent communication dependencies limit computation-communication overlap, reducing GPU utilization. Moreover, in cross-hardware (NUMA or node) architectures, due to imbalanced communication bandwidth, frequent communication synchronization will limit overall performance. Based on these insights, we propose CHARM+, Cross-Hardware Attention with Re-Merge Multistream Mechanism. We reorganize sequential communications into several levels and achieve intra-level parallelism and computation overlap. Furthermore, we decouple cross-hardware communication from intra-hardware communication, eliminating synchronization overhead caused by bandwidth imbalance. Forward and backward algorithms were evaluated on multiple hardware architectures and consistently outperformed state-of-the-art methods. Compared to Ring-Attention, our forward and backward algorithms achieve average speedups of 1.3x and 1.7x on a dual-NUMA PCIe architecture, and 2.8x and 2.9x on a dual-node NVLink architecture, respectively.

en
arXiv AI Papers

Retrieval Supersedes Scale: Efficient Log Level Prediction via Multiplex Socio-Technical Context

Developers insert logging statements in source code to record its execution, and the resulting logs are essential for detecting and troubleshooting system anomalies. A key part of these statements is the log level (e.g., DEBUG, INFO, WARN, ERROR), which determines whether a message is recorded. Choosing it is a trade-off: levels set too low mask important information in production, while levels set too high create noisy logs and extra I/O and storage overhead. Recent work uses Large Language Models (LLMs) with In-Context Learning (ICL) to predict log levels, but typically augments the prompt with randomly sampled examples. We argue that this overlooks the socio-technical nature of logging, where conventions vary by component and development team. Off-the-shelf LLMs using random examples are reported to achieve median AUCs of only 0.56 to 0.76, leaving room for improvement without fine-tuning. In this paper, we propose a retrieval approach for LLM-powered log level prediction that prioritizes context relevance over random selection and basic similarity. Our method retrieves logging examples relevant along two socio-technical dimensions: (i) functionality (code performing similar operations) and (ii) ownership (code maintained by the same developers). Evaluating four LLMs across ten popular Java projects, we find that this retrieval improves AUC over random baselines by 0.07 (median), and combining both signals yields median AUCs of 0.83 to 0.97. Our ablation studies show that each signal improves on random retrieval, and that combining them outperforms the stronger of the two on all ten projects. Our results also significantly exceed state-of-the-art supervised predictors (e.g., DeepLV) by a median AUC of 0.12 to 0.19. Our findings highlight the importance of socio-technical signals such as code functionality and ownership for LLM-powered log level prediction.

en
arXiv AI Papers

Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees

Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value. We show this targets a hard quantity in a state-observed testbed and propose a learnable, deployable reformulation instead. On valence-arousal-dominance trajectories from a dyadic corpus, repeating a speaker's own previous state sets a persistence baseline that no frozen-encoder correction meaningfully improves upon and a state-space filter exceeds; the floor requires the historical state to be observed, since an estimated anchor collapses persistence below a direct forecaster. What survives is the timing of a departure from persistence, learnable on three of four corpora and near chance on the highest-base-rate corpus, a negative result we report. We recast the task as selective departure forecasting: a lead-time-weighted metric with a leakage protocol, and commitment policies whose best choice switches with the departure rate. A dialogue-level conformal risk control bounds the expected loss of committed predictions, meeting the target in all twelve configurations tested, though the guarantee is bought through abstention, with coverage and alarm recall falling sharply on the hardest corpus. One tested language model's confidence fails as a ranking signal where another succeeds, a model-dependent failure not yet attributable to family versus scale. Code and result logs are available from the corresponding author upon request.

en
arXiv AI Papers

RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding

Recycling a target model's own predictions offers a training-free source of proposals for speculative decoding. In vision-language models, however, existing recycling indexes predictions by the last token alone, conflating predictions computed under different images and prefixes; we find that such reuse fails most often at image-sensitive decoding states. Longer keys reduce this aliasing but match fewer states. We introduce , which stores target predictions under one-, two-, and three-token keys: contextual memories live only for the current request and are thus implicitly conditioned on its image, while token-level memory persists across requests to retain coverage. At each lookup, entropy-confidence weighting fuses the retrieved predictions according to their key specificity and concentration. Best-first search composes the fused transitions into a candidate tree, supplemented by suffix-matched continuations, and one target pass verifies the tree under greedy decoding. Without training or an auxiliary draft model, \ achieves mean speedups over autoregressive decoding of 1.66and 1.56across seven single-turn benchmarks on Qwen2.5-VL-7B and LLaVA-1.6-7B, exceeding the strongest training-free baseline, Token Recycling (1.51and 1.37). Our implementation is available in https://github.com/Senmo996/RECAP-official-code.

en
arXiv AI Papers

CellCanon: An Agentic Cellular World Model for Prediction, Explanation, and Observation-Driven Updating

Biological discovery requires using molecular knowledge and new measurements to infer responses beyond the conditions already observed. We introduce CellCanon, the first agentic cellular world model to unify single-cell expression prediction, evidence-grounded explanation, and observation-driven updating. Its predictive core reuses condition-level biological evidence across gene-specific numerical readouts to guide single-cell expression generation. A shared world state links predictions, acquired measurements, and source-linked claims, supporting explanation and revision. On 339 held-out SciPlex3 conditions across three cell lines, CellCanon improves differential-expression AUPRC and Macro-F1 over the best baseline for each metric by 63.3% and 17.3%, respectively, and direction Macro-F1 by 7.2%. Relative to gene-wise reasoning on matched drug-cell cohorts, measured language-model token use falls by 99.77% for Predict and 98.41% for Explain. On the source-grounded benchmark, Explain correctly answers all answerable questions with supporting proofs and identifies all insufficient-evidence cases. In simulated experimental feedback, Update uses one measured source context per drug to exceed the best fine-tuned baselines in differential-expression AUPRC and Macro-F1 without changing model weights. Together, these capabilities support a cumulative account of cellular responses, with predictions and biological judgments that can be revised as evidence accumulates.

en
arXiv AI Papers

When Does Better Confidence Improve a Knowledge-Graph Audit?

Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass Δ^{cl}. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. On the held-out cross-document graphs, an error-rate fan-out queue leaves 3.98-4.74 percentage points more errors than a joint model with the same actions. By comparison, opening shared actions for that joint planner reduces residual errors by 0.89-1.43 points relative to its own fact-only plans, in point estimates. Equivalence between joint and independent-block models remains inconclusive. Generic LLM verification improves three of four model-budget configurations on each held-out set. LLM adjudication identifies possible benchmark omissions.

en
arXiv AI Papers

CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines

Large language model (LLM) shopping assistants now recommend products in multi-turn conversations. However, reliable evaluation faces Data scarcity and Difficulty Standardizing Criteria. To address these obstacles, we introduce CARTBench for CART (Complex and Ambiguous Requests with Timelines). For Data scarcity, we curate cases from real commercial shopping needs across 17 retail domains, pairing timestamped dialogue with 1,603 product records. For Difficulty Standardizing Criteria, we develop case-specific rubrics guided by Ideal Response Principles, distilled from excellent replies manually selected from successfully completed orders. These principles also guide Principle-Guided CART Prompting, our structured recommendation strategy. The experimental benchmark contains 1,328 expert-annotated criteria across Core, Excellence, and Safety. To answer the CART question, we evaluate 7 flagship commercial API models, including GPT-6.1-Sol and Claude-Opus-5, and 35B+ parameters open-weight models. In the first full-suite evaluation under the frozen rubrics, 3 of 10 models exceed 90% on Core, while none exceeds 45% on Excellence. Therefore, we identify an understanding-to-execution gap between required behavior and high-quality purchase advice. To examine these limitations, we diagnose shared failures in product evidence and unresolved needs, linked to changing requirements and decisive unknowns. Code and data are available at https://github.com/Da1yuqin/CARTBench.

en
arXiv AI Papers

PEARL: Prediction Error-Adaptive Regularized Learning for Selective Forgetting under Partial Preference Drift

User preferences shift as needs, context, and tastes evolve. This matters for personalized recommendation, LLM response generation, and RLHF-trained reward models, which can become miscalibrated as preferences drift. Existing non-stationary bandit methods forget uniformly across all dimensions, but real preference shifts are typically partial: some dimensions go stale while others remain valid. Neural contextual bandits accumulate confidence monotonically via the Gram matrix, with no mechanism to direct uncertainty where predictions have gone wrong. We propose PEARL (Prediction Error-Adaptive Regularized Learning), which reverses the Gram update along feature directions where predictions are surprisingly wrong, while leaving confidence intact elsewhere. We prove that (i) any non-adaptive policy suffers linear regret after a preference shift, (ii) no fixed exploration rate achieves low regret in both stationary and non-stationary regimes, and (iii) PEARL's cumulative regret scales with the number of shifted users N_s, not the total population N. On PRISM, a personalized LLM response selection benchmark (1,500 users, 21 LLMs), PEARL beats greedy by +4.0 points and the best neural bandit baseline by +2.5 points (p<0.001), while performing on par with greedy when preferences are stable. It beats sliding-window and discounted approaches by 3 to 10 points, showing that selective forgetting outperforms uniform forgetting. The selection policy is a ~100K-parameter MLP that runs in milliseconds on CPU, leaves LLM weights frozen, and works with any API-based model.

en
arXiv AI Papers

Vision Paper: Why Distributed LLM Post-Training and Decentralized Alignment Are Now Essential

This vision paper argues that distributed learning, including federated and decentralized, should become a first-class paradigm in LLM post-training, not merely a privacy add-on. Current methods like RLHF and DPO rest on an invisible assumption: preference data should be centralized. We contend this assumption is scientifically unjustified, practically unsustainable, and ethically problematic. As LLMs deploy into healthcare, law, finance, and multilingual communities, preference data originates from populations that cannot or will not centralize. We develop a three-pillar argument grounded in (1) privacy and data sovereignty, (2) pluralism and representational equity, and (3) robustness and scalability. We formalize key technical challenges unique to this intersection, reference drift, preference heterogeneity, and the DP-utility trade-off for contrastive losses, and propose concrete algorithmic directions, and sketch a research agenda. Our analysis shows distributed post-training is not only necessary but tractable, and ignoring it risks AI that is legally noncompliant, representationally narrow, and brittle at scale.

en
arXiv AI Papers

Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning

Firms using large language models under fixed budgets must decide which model to call and whether to retry a failed task. Because a call's charge is revealed only after completion, one long response can exhaust the remaining budget and leave later tasks unserved. Our objective is to maximize the number of tasks solved before service stops. We develop a contextual bandit policy, ADP-HT, which learns each model's task-specific success probability and constructs conservative cost estimates from coarsened response-length labels on a quantile grid with 2^K intervals. The policy weighs predicted success against these costs, adjusting the cost penalty to realized spending and the budget available per remaining task. Under calibration, local regularity, and grid-coverage conditions, we bound the excess allowance in the policy's conservative cost estimates. At a fixed sample size, increasing K reduces the discretization term but increases the estimation allowance. At the tightest tested budgets, ADP-HT solves more than twice as many MATH500 and GPQA tasks as the best implemented baseline. It achieves the highest mean cumulative score at ten of fourteen RouterBench budgets. On LiveCodeBench, it outperforms a deployed commercial router in both default and cost-saving modes at the three lowest test budgets.

en
arXiv AI Papers

TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration

Decision models choose among predefined options in tasks such as routing and action selection. In multi-agent collaboration, a decision determines how members divide work, exchange resources, and act in parallel. We introduce TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios where coordination choices affect goal completion. Models receive complete global information and candidate team plans, with reference answers established through execution and exact search. Models select an optimal team plan and, in paired variants that retain or remove it, judge whether better arrangements exist beyond the supplied options. We evaluate 40 native decision models and compare them with 10 general-purpose language models. The best native decision model achieves 62.50% decision accuracy. Native decision models remain close to chance in optimality verification. Paired tests reveal that some report better alternatives regardless of whether an optimal plan is already present. These findings show that team-plan decision accuracy alone can conceal systematic errors in judging whether the supplied options contain an optimal arrangement. The dataset and evaluation code are publicly available at https://github.com/lililibaohang/TandemBench.

en
arXiv AI Papers

A Hybrid Approach for Automated Security Pattern Recovery

Security-by-design emphasises integrating security into software design and development. Security pattern catalogues operationalise this principle by prescribing reusable architectural solutions to recurring security problems. However, recovering their implementations from source code remains challenging because security patterns are abstract, span multiple components, and admit many valid implementations. We present SecPatRec, a hybrid approach for automated security pattern recovery from source code repositories. We treat a security pattern as a reference architecture and frame its recovery as a deductive task: determining which prescribed roles are present, grounding them in code entities, and recovering their interaction sequences. SecPatRec pairs a ReAct-style LLM agent equipped with semantic and lexical code search for role detection and grounding with static code property graph analysis for interaction recovery. We curate a human-validated ground-truth dataset of 100 pattern instances covering five security patterns across 93 open-source Java and Python repositories, and introduce a three-level evaluation framework measuring recovery correctness against this ground truth. We evaluate SecPatRec using four LLMs, including proprietary and open-source models. Averaged over all models and pattern instances, SecPatRec achieves role-detection accuracy of 0.84, role-grounding similarity of 0.84, and an interaction-recovery score of 0.66. Compared to a one-shot end-to-end LLM baseline, SecPatRec achieves higher aggregate recovery scores and lower estimated LLM API costs per run, while processing repositories that exceed the baseline's configured input limit. The recovered role mappings and statically derived interaction sequences provide structural and behavioural evidence that can support inspection of security-pattern implementations.

en
arXiv AI Papers

Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents

Large language models increasingly automate complex tasks, but human decision capacity does not scale with their capabilities. In many applications, humans remain essential for providing private context, authority, or judgments unavailable to the agent. We formulate human decision capacity allocation: given multiple consultation opportunities and a limited budget, at which decisions should an LLM agent consult a human? The central challenge is estimating consultation value, which is executor-dependent because the same human input may benefit different downstream agents differently. We introduce Consultation Value Distillation (CVD), which estimates consultation values offline using Monte Carlo executor rollouts and distills these values into lightweight predictors for budgeted allocation, requiring no rollout-based value estimation at deployment. Across five batch and three sequential settings with two frontier executors, CVD improves allocation through joint and continuation-aware value learning, while independent consultation values remain competitive in several settings. CVD also broadly outperforms direct prompting and Value of Information where applicable, remains robust with substantially less rollout supervision, and enables nearly lossless approximate allocation at low search cost.

en