跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 09:09 — 2026-11-09 09:09（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 07:12最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 07:10（北京时间）
新论文 · v1arXiv:2610.37962

Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence

Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos

原文摘要

Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This flexible design introduces new sources of structural bias. This paper studies positional bias in top-1 and single-turn LLM-based RS: systematic dependence of the recommended item on the order in which candidates are presented in the prompt. We propose two complementary detection methodologies: (i) POB-ICM, based on contingency matrix analysis and Chi-square independence testing, and (ii) POB-UNBP, a sample-efficient approach derived from a uniformity null model under permutation-based evaluation, enabling stochastic decoding with formal statistical guarantees. Using a controlled RAG testbed for product recommendation, built on a real product catalog, a fixed prompt template and 2000 template-generated user queries with 20 permutations each (40,000 instances), both methodologies reject the null hypothesis of positional independence and uniformity in all evaluated state-of-the-art models. We introduce three complementary metrics -- permutation sensitivity, positional bias, and strong positional bias -- to quantify this effect, the latter targeting cases where the position displaces the recommendation towards clearly less relevant items rather than only choosing among comparably relevant ones. A robustness analysis across candidate-set size and decoding temperature shows that the bias is structural and model-dependent, not an artifact of deterministic decoding or candidate-set size. These results establish positional bias as a measurable, reproducible property of prompt-mediated recommendation pipelines in the evaluated setting and motivate routine auditing and governance controls (e.g., order randomization, standardized prompting) for deployed LLM-based RS. Source code is publicly released.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37952

SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation

Haoran Liu, Guanyi Wang, Yu Yang

原文摘要

Rounded capacity cuts (RCCs) are among the most effective cuts for capacitated vehicle-routing relaxations, but exact separation is computationally prohibitive at scale. Existing heuristic and neural separators can be fast, but often fail to produce sufficiently many effective cuts within practical separation budgets. We introduce SAG-Sep, a separator that scores node membership in RCC-inducing subsets across vehicle-count levels from a fractional LP solution in a single encoder forward pass, avoiding the iterative predict-and-coarsen inference used by NeuralSEP-style separators. SAG-Sep encodes the LP solution as a Sparse Augmented Graph (SAG), adding flow-informed multi-hop edges that expose long-range routing structure without densifying attention. Beyond LP-aware sparse encoding, we observe that high-value exact RCCs are typically nested, organizing into onion-like subset families, and SAG-Sep's node scores track subset nesting depth. This motivates Onion-Sweep (OS), a training-free decoder that ranks customers by their scores, evaluates the RCC violation of every prefix of the ranking in one vectorized pass, and emits the most violated prefix of each replica together with a cross-replica family of nested proposals, converting independent node scores into structurally coordinated RCC candidates without a tuned threshold or probing band. On the NeuralSEP benchmark with N=1000 customer instances, SAG-Sep with OS reduces the average root gap by 17.7% relative to the strongest NeuralSEP baseline, while the single-pass SAG-Sep separator achieves a roughly 30-fold per-iteration neural separation speedup. Our findings suggest that LP-aware sparse encoding and the nested structure of high-value cuts are structural patterns worth leveraging in neural separation more broadly.

cs.LG · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37935

SkillMem: Compact External Skill Memory for Latent Multi-Agent Reasoning

Yuxuan Zhu, Mohammad Mohammadi Amiri, Pin-Yu Chen, Keerthiram Murugesan

原文摘要

Latent multi-agent systems reduce inference cost by keeping intermediate reasoning and inter-agent communication in continuous representations.\ Reusable skills, however, are commonly supplied as text or stored as layer-wise Key-Value states or skill-specific model parameters, introducing repeated processing or substantial per-skill storage.\ We introduce \textbf{SkillMem}, which represents each reusable skill as a small external latent memory and makes it directly available during latent multi-agent reasoning.\ A role-conditioned cross-attention reader allows the same memory to guide different agents according to their roles and current hidden states.\ We train the skill memories and shared reader through behavioral distillation, matching the change in token predictions induced by a textual skill while keeping the backbone frozen.\ For our experiments, we obtain textual skills from paired successful and failed multi-agent trajectories, although existing skills can also be compiled directly.\ Across six benchmarks and Qwen3 models ranging from 4B to 14B parameters, SkillMem provides strong gains for smaller backbones while preserving efficient latent multi-agent inference across model scales.\ We use the same $8\times256$ memory configuration across all evaluated model scales, requiring 9.6\,KB of skill-specific storage per skill, including its retrieval embedding.\ For a library of 100 skills, SkillMem reduces total storage by more than $38\times$ compared with alternative skill representations and achieves up to a $4.23\times$ end-to-end inference speedup.\ These results show that compact procedural memories can be reused without sacrificing the efficiency of latent multi-agent reasoning.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37933

NLP-based Message Prioritisation for Opportunistic Routing: A Case Study of Nepal Earthquake Emergency Communication

Yihang Cao, Milena Radenkovic

原文摘要

This dissertation investigates whether Natural Language Processing (NLP) based semantic message prioritisation can improve the treatment of urgent disaster messages in opportunistic emergency communication, using the 2015 Nepal earthquake as a case study. TF IDF with Logistic Regression and BERT are used to classify social media messages into nine humanitarian categories, which are mapped to four routing priorities from P1 to P4. These priorities are integrated into the ONE simulator within a controlled Kathmandu earthquake scenario using a modified Binary Spray and Wait router. BERT achieves higher priority accuracy and P1 recall than Logistic Regression, while reducing under prioritisation and severe priority errors. However, improved NLP performance does not produce uniform network gains. P1 delivery probability remains high and similar across routing conditions, and no consistent latency reduction is observed. The clearest difference appears under buffer pressure, where the BERT condition shows fewer observed ground truth P1 buffer losses than Logistic Regression. The results indicate that semantic prioritisation is most valuable when limited transmission and storage resources are contested, although it cannot overcome mobility and contact constraints in opportunistic networks.

cs.NI · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37932

Understanding Large Language Models as Numerical Optimizers

Lingyun Guo, Ali Bereyhi

原文摘要

Large language models (LLMs) have emerged as potential tools for numerical optimization. Despite promising results, their intrinsic optimization capabilities and limitations remain poorly understood, particularly in high dimensions. This paper investigates the ability of LLMs to exploit mathematical problem structures and generate feasible, near-optimal solutions. We develop an evaluation framework that distinguishes solution quality from execution failures, including numerical inaccuracies, constraint violations, and output-format errors. Using representative problems from convex optimization, fractional programming, and constrained projection, we assess LLM performance against deterministic reference solvers across different dimensions. Our results reveal that LLMs can capture useful optimization structures and produce near-optimal solutions, even when their outputs fail to satisfy numerical or formatting requirements. However, reliability deteriorates with increasing problem dimension and depends strongly on the underlying optimization structure. To further investigate the limitations, we deploy an iterative refinement mechanism that provides targeted feedback on feasibility and solution quality. The results demonstrate that iterative refinement substantially improves reliability and extends the range of problem dimensions over which LLMs produce valid solutions. Nevertheless, persistent numerical and structural errors limit their applicability as standalone optimizers. These findings provide insights into the capacity and limits of LLM-based optimization and motivate hybrid approaches that combine LLM reasoning with deterministic numerical verification.

cs.AI · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37926

GARDEN: Generalist Autonomous Reward Design Through Evidence Navigation for Cooperative Multi-Agent Reinforcement Learning

Dogan Urgun

原文摘要

Cooperative multi-agent reinforcement learning (MARL) enables teams of agents, such as robots and autonomous vehicles, to learn coordinated behavior, but what such teams learn is largely determined by their reward function. Because task success alone provides too little guidance for learning, intermediate rewards are usually designed by hand, and this effort must often be repeated whenever the environment or the team changes. Large language models (LLMs) can automate the effort by writing reward functions as code, yet the resulting rewards are typically designed and tested in a single setting. To enable their reuse across settings, GARDEN (Generalist Autonomous Reward Design through Evidence Navigation) is proposed, in which one reward program is developed for a family of related scenarios and transferred, unchanged, to scenarios that were not available during its design. During development, environment code, training records, and agent behavior are investigated by an LLM reward engineer, and draft rewards are tested in trial training runs, while the learning algorithm and the rule for selecting the final reward are held fixed. On unseen scenarios of the Overcooked and SMAX benchmarks, task returns were increased by 58.2% and 52.5% over the default rewards on two kitchen layouts, and the mean win rate in two combat scenarios was raised from 51.0% to 89.9%. Under matched candidate and probe budgets, this exceeded the 84.2% and 79.2% obtained with fixed diagnostic feedback and Eureka-inspired reward reflection. These results show that a single autonomously engineered reward can be reused effectively across related cooperative scenarios.

cs.AI · cs.MA · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37923

VerifiedLab: Harnessing Knowns for Unknowns

Yu Yao, Jiayi Dong, Yang Yang, Shuiwang Ji, Ju Li

原文摘要

Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harness framework for this human-to-machine transition of knowledge. VerifiedLab transforms research output from passive artifacts into active systems that accelerate downstream use, adoption and prediction of future trends. In VerifiedLab, a team of AI scientists with distinct roles reasons over records verified field by field: a principal investigator plans, a librarian computes the evidence directly from the records, specialists draft, and a gate and a critic check each claim against the measured reliability of its data before the harness decides whether to release or withhold it. We demonstrate the efficacy of VerifiedLab through extensive experiments on perovskite solar cells: VerifiedLab recovers known physical trends, anticipates devices reported a year later, and lets AI scientists inherit the literature together with a measure of how far it can be trusted. By scaling the inference-time verification compute, VerifiedLab introduces a new pathway for knowledge dissemination and machine harness for AI co-scientists.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37919

SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World

Yusheng Zhao, Bowei He, Xue Liu, Mingxiao Li

原文摘要

Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs, and do not separate empirical evidence from pretrained priors. We introduce SciGame, a controlled benchmark that converts scientific literature into structured scientific cards. Each card yields a pair of Original and dimensionally consistent Counterfactual environments with the same task interface. SciGame contains a Historical collection of canonical laws and a live Temporal collection curated from papers published after model knowledge cutoffs. It evaluates agents in candidate-guided Identification and open-ended Discovery settings. Each setting runs under Prior-only, Fixed, and Adaptive protocols. Experiments on five frontier models yield three findings. First, familiar priors hurt performance once the governing relation is altered. Second, adaptive experimentation helps the strongest models but harms weaker ones under limited budgets. Third, good explanations can hide quantitative failures. Recovering the exact symbolic form remains the main bottleneck, even when agents interpret evidence correctly. Current agents can investigate systems actively, but inducing exact laws in unfamiliar settings remains an open challenge.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37917

What Actually Matters? A Paired Evaluation of Inference Settings for $π_{0.5}$ on BEHAVIOR-1K

Ruben Hammele, Samira Huber, Mohammad Nazeri, Amirreza Payandeh, Alexandyr T. Card, Aaron Nguyen, Anuj Pokhrel, Daeun Song 等 10 位作者

原文摘要

Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale settings do not necessarily generalize to large-scale, diverse task suites. To address this gap, we conduct a systematic, paired evaluation of previously proposed inference and data-collection strategies across all 100 tasks. Our evaluation uses a fine-tuned $π_{0.5}$ model based on the 2025 BEHAVIOR Challenge winner, which achieves a Q-score of 0.39 on the public test set. These results show that proposed strategies do not transfer uniformly to new environments and tasks. Project page, videos, and detailed analysis: https://rubenhammele.github.io/behavior2026

cs.RO · cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2608.02829

Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling

Ravi Satya Durga Prasad Yenugula

原文摘要

Model families are trained size by size. Can a pretrained large model instead be converted into a smaller sibling? We characterize the 1.4B->410M conversion in Pythia end to end. Representations align strongly across sizes (ridge R^2=0.84); parameters align weakly. Dense weight projection is destructive; a bit-exact control places the fault in basis mixing, which breaks rotary, per-head, GELU, and LayerNorm structure. Residuals after the best-fit linear operator carry no learnable or transferable signal under shuffle controls, so conversion value lives in initialization. Matched-budget continued pre-training separates two independent levers, least-squares compensation (function lever, best zero-shot) and variance-preserving rescale (dynamics lever, best endpoints), with a placement rule read off the architecture: compensation is well-posed exactly where no normalization sits between cut and read; norm-fronted paths take rescale. At 30M tokens compensation beats the best subcloning variant on a width-reduced pair (84.6+-2.1 vs. 90.7+-3.8, 6/6 seeds) and a held-out depth-reduced pair (109.3 vs. 117.9, 3/3 seeds); the two reach parity at 33x the budget, and at ~5x the donor scale the levers anti-synergize. A second family, Qwen3-1.7B->0.6B (RMSNorm, SwiGLU, grouped-query attention), takes the placement rule unchanged but reverses a 2x2 crossing the re-fit with the activation statistic it reads: on Pythia the re-fit carries the gain and the statistic adds 2.3 perplexity; on Qwen3, with far more heterogeneous MLP unit energies, the statistic carries 66 points and the re-fit is a null on top. Informed selection + compensation + rescale is the best arm in both families, 19x and 23x lower perplexity than from scratch at matched budget (2.94 and 3.13 nats), and beats structured pruning plus distillation. Code, checkpoints, and the frozen eval corpus are released.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37909

TERRA: Task-Oriented Edge AI for Regional Fire Detection with Identity-Free Reporting

Mohammad Kazemi, Julie A. McCann

原文摘要

Distributed fire-monitoring systems may involve many sensing devices reporting over a shared uplink, even though the operational objective is often to identify regions exhibiting evidence of fire rather than to recover device-specific measurements. We introduce TERRA (Task-Oriented Edge Representation and Regional Aggregation), an edge-AI framework that combines task-oriented local inference, identity-free region-tagged reporting, and permutation-invariant regional evidence aggregation. TERRA supports two reporting modes: TERRA-Score, in which each device communicates a quantized local fire probability, and TERRA-Feature, in which it communicates a compact learned representation for receiver-side aggregation using a permutation-invariant DeepSets model. Using all 15 numerical sensing modalities of the distributed indoor EN54 fire-alarm dataset as a proof-of-concept testbed, we evaluate regional inference for an episode-level fire-scenario target under repetition-disjoint three-fold cross-validation. We study representation size, task-payload quantization, report availability, and robustness to missed and false recovered messages. With nine reports and perfect message recovery, TERRA-Feature achieves mean AUPRC 0.990 using a 24-bit task payload, while TERRA-Score achieves 0.987 using only 6 bits; both attain an MDR of 1.81% at FAR $\leq$1%. TERRA-Feature achieves slightly higher AUPRC under reliable recovery, whereas the more compact TERRA-Score is less sensitive to increasing false-message contamination.

cs.LG · cs.AI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37906

Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons

Aurora Micheli, Claudio Gallicchio, Nergis Tomen

原文摘要

Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is triggered by sparse spikes rather than executed densely at every timestep. However, existing spiking reservoirs almost exclusively rely on Leaky Integrate-and-Fire (LIF) neurons, whose low-pass dynamics limit their ability to distinguish information encoded at different temporal frequencies. We introduce HRF-Res, a liquid state machine in which LIF neurons are replaced by a heterogeneous population of Harmonic Resonate-and-Fire (HRF) neurons. These neurons exhibit intrinsic oscillatory dynamics and selectively respond to input frequencies, enabling the reservoir to capture frequency-specific temporal patterns. The result is more discriminative representations and higher classification accuracy than LIF-based reservoirs, achieved without sacrificing the energy efficiency of spiking computation, with up to 19x lower energy consumption than an equivalent non-spiking oscillatory reservoir. Evaluated on ten benchmarks spanning time series, sequential images, audio spike trains, and neuromorphic vision, HRF-Res achieves state-of-the-art accuracy among spiking reservoir methods. These results demonstrate that introducing frequency-selective dynamics into spiking reservoirs improves representational quality and classification performance while preserving their inherent energy efficiency.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37905

FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision

Wentao Zhang, Yilei Zhao, Guangyan Gan, Shuo Sun, Lin William Cong

原文摘要

Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 companies under distinct information constraints. An evaluator separate from the acting agents scores final filings and responses against 6,099 eligible requirements and audits unsupported claims and harmful revisions. Our framework couples iterative review and revision within each case with procedural learning across cases, converting requirement-level evaluation feedback into role-specific guidance without updating model weights. Updates affect only subsequent cases, allowing procedural adaptation to be assessed without retrying scored tasks. On the evaluated stream, evolution increases requirement fulfillment from 24.28\% to 27.96\% and full comment resolution from 16.90\% to 20.75\%, with a 5.8\% increase in total cost over the fixed-policy variant. FilingLoop connects the concerns an agent discovers with the company facts it obtains and the revisions it commits, providing requirement-level feedback for procedures used in later review tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37903

Think Twice: The Metis-1.6 Technical Report

Giulianno Vollmer

原文摘要

Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its latest step: two language models built from scratch by a single researcher, Praxis (2.94B parameters, 0.46B active per pass) and Logos (10.23B parameters, 1.18B active per pass). Both run a hybrid Mamba-2 and attention mixture-of-experts stack twice for every token, so each token gets a second look. Each was trained on 1.02T tokens in total: 804.76B of pretraining, 18B of context extension to 131,072 tokens, and 200B of supervised fine-tuning. Metis-1.6 was never meant to challenge frontier models, and across 40 post-trained benchmarks it mostly does not: Logos averages 52.93, seventh of 17 models in its comparison set and within a point of Qwen3-4B. But it gets there on roughly a twelfth of the median training data of the comparators that disclose it, and with fewer active parameters per token than any model that beats it, which puts it on the Pareto frontier for both. In mathematics it ranks second of 30 models, with 67.50% on AIME 2025 and 63.64% on HMMT February 2026. It is weak at code, instruction following and long context. The rest of the report is the part I found most valuable: what went wrong. The optimizer I configured never ran, and attention trained with AdamW for all of pretraining. A 1.77B-parameter n-gram memory learned to switch itself off. Five fine-tuning choices cost capability. And a length reward under group-mean normalization punished correct solutions for being long once a group's pass rate passed 2/3, a sign inversion I prove and fix with a one-line clamp. I close with the 10B-token ablations behind MoRE (Mixture of Recursive Experts), the looped architecture of Metis-1.7.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37901

Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

Parth A. Gandhi, Avital Aviv, Prasanna N. Wudali, Yuval Elovici, Asaf Shabtai

原文摘要

An agent skill packages natural-language instructions, scripts, and reference files that an LLM-based agent loads for a task. Skills may access the file system, shell, and network under user-authorized permissions; weaknesses can lead to unsafe execution. Existing scanners primarily target malicious skills, not unintended vulnerabilities in public repositories, and analyze skills in isolation, overlooking multi-skill interactions. To address these gaps, we developed a six-module scanner: Content Extraction, Local Analysis, Composite Analysis, Validation, Reporting, and Mitigation. Local Analysis detects unintended vulnerabilities in benign skills. On a 556-case leaderboard subset of SkillTrustBench, it achieved 95.90% recall with a 4.22% false positive rate; on a balanced sample of 1,000 MalSkillBench skills, its F1 was 0.947, outperforming Cisco's Skill Scanner, NVIDIA's SkillSpector, AgentSkillsScanner, and SkillSieve. In 1,587 skills from the 75 most-starred GitHub repositories, three analysts confirmed 53 of 59 findings (89.8% precision) across 23 repositories. We developed proof-of-concept (PoC) attacks for each vulnerability, disclosed 10 medium- and high-severity cases to maintainers, and tested mitigations on the remaining cases. Composite Analysis models dependencies among skills through shared resources, invocations, and instruction-mediated interactions. On SCR-Bench, its F1 score was 0.991 (98.7% precision, 99.6% recall), versus 0.816-0.858 for three SkillsGuard configurations released with CompoSkill. It identified two composite findings on GitHub, validated by PoC attacks. The Mitigation module recommends skill substitution, patches, and configuration changes. For 47 of 55 GitHub findings, mitigations prevented PoC attacks in all trials while preserving tested legitimate functionality.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.11512

EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

Jinane Bazzi, Mariam Rakka, Fadi Kurdahi, Mohammed E. Fouda, Ahmed Eltawil

原文摘要

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, automotive and robotic computing platforms, and high-performance embedded systems, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by GEMV operations that are inherently memory-bound, resulting in poor utilization and prohibitive energy costs at the edge. In this work, we present EdgeCIM, a hardware-software co-design framework for accelerating autoregressive decoding of SLMs on edge devices in latency-critical applications. At its core is a CIM macro, implemented in 65 nm, coupled with a tile-based mapping strategy that balances pipeline stages, maximizing parallelism while alleviating DRAM bandwidth bottlenecks. Our simulator enables design space exploration of SLMs up to 4B parameters, identifying hardware configurations that optimize latency and energy according to a configurable objective function. On LLaMA3.2 3B (INT4), EdgeCIM achieves 1.76x and 3.21x higher throughput than NVIDIA Jetson AGX Orin and Orin Nano Super operating in MAXN mode, respectively, and 7.07x higher throughput than Qualcomm's Snapdragon-X Elite. Extensive benchmarks on TinyLLaMA 1.1B, LLaMA3.2 (1B, 3B), Phi 3.5 mini 3.8B, Qwen2.5 (0.5B, 1.5B, 3B), SmolLM2 1.7B, SmolLM3 3B, and Qwen3 (0.6B, 1.7B, 4B) reveal that our accelerator, at INT4 precision, achieves on average 336.4 tokens/s and 173 tokens/J. These results establish EdgeCIM as a compelling solution towards real-time, energy-efficient, latency-critical SLM inference at the edge.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37896

The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning

Yifan Wang, Leixin Zhang, Jinyi Mu, Yu Wang, Mayank Jobanputra, Isabel Valera, Vera Demberg

原文摘要

Subjective judgments such as offensiveness often vary substantially across individuals, motivating pluralistic modeling approaches that incorporate annotators' socio-demographic information to capture this variation. However, prior findings on the benefits of socio-demographic information for pluralistic modeling are mixed, calling for a systematic analysis of both its effectiveness and the mechanisms through which it improves prediction. In this work, we study $\textbf{when}$ and $\textbf{where}$ socio-demographics benefit pluralistic offensiveness modeling, as well as $\textbf{the role of explicit reasoning}$ in leveraging this information. Across three multi-annotator datasets with prompted and trained LLMs, we first show that demographic gains are small and inconsistent for individual predictions but become clearer at the group and population levels, because aggregation attenuates the idiosyncratic variation that masks small but systematic demographic signals. Second, using a reasoning and prediction format that explicitly decomposes individual judgment into an overall baseline and a demographic-specific deviation, we show that the gains arise from both components: demographic information improves baseline estimation and enables meaningful demographic-specific shifts, and interventions show that better component estimates improve final predictions. Finally, comparing direct demographic conditioning with explicit reasoning about how the text interacts with annotator demographics, we find that reasoning yields more accurate baseline and shift estimates as well as final predictions, whereas conditioning alone rarely produces informative shifts. These results suggest that the mixed evidence in prior work may partly stem from individual-level evaluation, and that the value of socio-demographic information depends on both how it is evaluated and how models are guided to use it.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.23927

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

Linhan Wang, Zijian An, Mingyuan Zhang, Chen Dai, Yi Xu, Can Cui, Jiayan Wang, Zichong Yang 等 11 位作者

原文摘要

Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchronous video generation at control rate is latency-prohibitive, while abandoning test-time visual imagination sacrifices task success. We show that visual imagination achieves both real-time inference and superior success rates when generated asynchronously off the critical path and consumed directly in latent space. We introduce GlanceWAM, which decouples imagination from control on a single shared video DiT backbone: an asynchronous proposer glances ahead on a slow clock to imagine a single lookahead frame seconds into the future in the background, while an action head decodes action chunks at control rate (48 ms) purely in latent space without blocking. Enabled by a non-interfering attention mask that isolates video representations and staleness-robust horizon training that accommodates asynchronous lookahead aging, GlanceWAM breaks the speed-success dilemma. Trained purely on demonstrations, it attains 72.2% on the 24-task RoboCasa kitchen benchmark (vs. 67.1% for synchronous Cosmos Policy) and 99.0% on LIBERO while cutting per-chunk control latency 24x relative to synchronous world-action models (48 ms on one A100). In single-arm and bimanual real-robot manipulation, it achieves higher average success than $π_{0.5}$ without any robot-data pretraining. Code is available at https://github.com/linhanwang/GlanceWAM and real-robot videos at https://linhanwang.github.io/glancewam/.

cs.CV · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37891

When More Planning Hurts: Learned Planners for World Models

Josef Chen

原文摘要

On PushT, our fixed action updater (1,505 parameters) solves 8 of 16 scenes reserved from our configuration selection. The comparison planners perform as follows: Selected Adam (7 tasks solved, total planning and encoding time 218.440s), adapted iCEM (2 tasks solved, total planning and encoding time 49.309s), released LePlanner (16 tasks solved, total planning and encoding time 5.652s). The total planning and encoding time for our action updater is 59.079s. Note that our action updater does not satisfy the task-cost criterion we fixed before evaluation. We also conduct another matched experiment where we only replay the first ten commands in each context and then allow the next solve 4, 8 or 12 updates (subsequent solves all get 8 updates). Among all 16 contexts (8 scene clusters), the 3 budgets get 9, 8 and 7 successes, respectively. Interestingly, the extra updates did not rescue any failing task in this experiment. All the changes in success/failure happen in one scene cluster, where we observe that the extra updates decrease the costs of the selected latent world-model trajectories for our updater, while the tasks that used to be successes become failures. The code, weights, evaluators, execution traces and cost accounting accompany the paper.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37875

Verification Learning Theory: A Process Model of Checking and Retention in AI-Assisted Judgment

Christoph Trattner

原文摘要

Accurate AI assistance can improve immediate judgments while reducing opportunities to practise the operations needed for independent performance. Verification Learning Theory (VLT) formalises this possibility for claim-evaluation practice followed by correct, independent, rule-specific feedback. The model links perceived assistant reliability to evidence checking and links the history of those checks to retained rule use. Its strict form assumes that task demands and perceived reliability influence learning only through checking, with equal learning per genuine check. It therefore predicts that perceived fallibility can improve delayed unaided judgment even without observed assistant errors, and that this advantage disappears when checking is already required and performed. Rule-specific gains and forecasts from checking histories provide further tests. Simulations examine the consequences and parameter dependence of these commitments; they do not constitute empirical validation. Comparisons with depth-of-processing and feedback-encoding accounts identify where predictions diverge and where the accounts remain observationally equivalent. The framework specifies experiments that can test the proposed mechanism and separates retention of practised rules from the broader problem of recognising which rule applies to a new claim.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37874

PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP

Md. Nakib, Sudipto Sarkar, A. J. A. Jubayer Talukder, Mohammad Ariful Haque

原文摘要

Deepfake detectors are almost always deployed as the single checkpoint that scored best on a validation split, yet the reliability of that choice is rarely measured. We measure it with PairCLIP-SWA, a single-backbone detector that adapts an OpenCLIP ViT-L/14 visual tower by progressive block unfreezing on a class-balanced corpus built by CLIP-similarity-guided one-to-one subsampling, and averages the fine-tuning trajectory in weight space. Trained in-domain on the IEEE SP Cup 2025 (DF-Wild-Cup) benchmark under the same protocol as the strongest published three-backbone ensemble, the weight-averaged detector reaches 97.04% accuracy, 98.64% AU-ROC and a 4.07% equal error rate, against 94.46%, 97.60% and 5.00%. Its training log shows why averaging matters: over the averaged epochs the non-averaged checkpoint swings across 5.34 points of validation accuracy while its validation loss more than doubles, whereas the average is never worse and is up to 5.99 points better. On an OpenForensics-derived benchmark the same instability becomes a misranking: the checkpoint that validation accuracy selects (98.43%) scores 88.85% on a disjoint 10,905-image test partition, rejecting 21.1% of genuine photographs, while the terminal average, ranked last on validation, scores 94.76%. A study of twenty-two in-house configurations on the identical DF-Wild-Cup split, including preprocessing ablations, shows that CLIP pre-training rather than ensembling drives accuracy, that secondary face cropping costs about 34 points, and that frequency-domain inputs transfer poorly. We recommend per-class selection criteria measured off the early-stopping split.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.02436

Agentic AI for Clustering and Relationship Discovery in Prediction Markets

Agostino Capponi, Alfio Gliozzo, Brian Zhu

原文摘要

Prediction market platforms list thousands of contracts whose logical and economic connections are implicit in their resolution rules. We introduce a hierarchical agentic reduction (HAR) pipeline for constructing inspectable cross-event relation graphs and a behavioral benchmark for evaluating their alignment with market prices. This partitions a catalog of prediction markets, specified by question and resolution text, into topic clusters, applies typed LLM reasoning to small batches, and proposes signed relations with rationales between specific markets. We evaluate semantic relation graphs spanning eight monthly Kalshi catalogs (February to September 2026). Using data from 30.3 million trades, we compute a benchmark that compares linked pairs' signed price-change correlations with those of matched, unlinked controls from the same topic cluster on identical timestamps. Under full-sample and leave-first-week-out evaluation, relations identified by our pipeline exhibit higher signed Pearson price-change correlations, with statistical significance, than matched within-topic controls. This increase also appears under Spearman correlation and becomes larger among relations labeled as medium or high strength. This benchmark provides a criterion for comparing relation-discovery methods against observations beyond their input text, and our results indicate the ability of agentic AI and LLM reasoning to identify meaningful relations between individual markets in connected Web marketplaces.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37867

What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine

Saransh Kumar Gupta, Akshadha Sharma, Lipika Dey, Partha Pratim Das, Ramesh Jain

原文摘要

Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation. We ask what happens to food similarity beyond identity: how different visual representations organize foods into relational neighborhoods, what culinary relationships these neighborhoods reveal or obscure, and how consistently these structures emerge across representations. Indian cuisine provides a challenging setting in which visually similar foods may have different culinary identities, while foods within a culinary family can vary substantially in appearance. Using an expanded Khana dataset and seven pretrained visual representations spanning convolutional, transformer-based, self-supervised, and image-text aligned models, we evaluate image-to-image retrieval and image-to-dish neighborhoods, examining culinary-family structure, contrast cases, and cross-representation agreement. We also aggregate image representations to compare dish-level visual similarity across models and against recipe-derived similarity for the same dishes. Image-level neighborhoods vary substantially across representations, including similarities across culinary-family boundaries. At the dish level, aggregation reveals common visual structure despite local variation, but this structure corresponds less strongly with recipe-derived similarity. These findings show that recognition performance alone cannot characterize relational structure: food similarity depends on representation, modality, and abstraction level rather than being a fixed property of the food collection. Understanding these structures is therefore a prerequisite to combining multiple food information modalities into a coherent notion of similarity.

cs.AI · cs.CV · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37865

Echo: Scaling Visual Reinforcement Learning with Off-policy Experience

Gagan Khandate

原文摘要

Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently, two-stage teacher--student distillation is commonly used to train visual policies, but introduces an imitation gap. In this preliminary study, we introduce \echomethod{}, \textbf{a single-stage off-policy RL framework that scales experience collection without proportionally increasing visual computation}. Through \textbf{inverse distillation}, a state-based auxiliary policy imitates the evolving visual policy and collects inexpensive, unrendered experience. Echo leverages this experience for off-policy value learning, directly improving the visual policy through a shared privileged critic. We instantiate \echomethod{} with FastTD3 and evaluate it on three visual control tasks and two dexterous manipulation tasks in Genesis. Relative to \sdpgmethod{} under the evaluated configurations, Echo reduces time to reference returns by an average of \textbf{60\% across the three locomotion tasks} and \textbf{56\% across both hand tasks}, while improving peak mean returns by \textbf{62\% and 12\%}, respectively. Both hand tasks also achieve higher mean returns at matched simulator-transition budgets. These initial results suggest that scaling off-policy experience is a promising approach to efficient direct visual RL.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.11311

Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble

Bingchen Wang, Zi-Yu Khoo, Jingtan Wang

原文摘要

Large language models are increasingly used as proxies for human subjects in social science research, yet external validity requires matching the response distributions of target human populations. We study population-level survey alignment: reconstructing aggregate survey responses from limited public survey data, without individual-level demographic profiles or model finetuning. We formalize this problem as preference reconstruction: rather than matching proxy agents to demographic profiles, we construct a functional basis of proxy agents and recover population preferences by weighted aggregation. We instantiate this idea via Prompts to Proxies ($\texttt{P2P}$), a two-stage inference-time system. Stage 1 uses structured attribute-based prompting with entropy-guided adaptive sampling to construct a diverse proxy pool spanning the latent preference space. Stage 2 employs L1-regularized regression to select a compact weighted ensemble matching observed target-population responses. Across 14 American Trends Panel waves, $\texttt{P2P}$ achieves an average test MSE of 0.014 at approximately 0.8 USD per survey, improving over prompting and demographic-conditioning baselines. On the World Values Survey, cross-locale transfer experiments show that basis expressiveness can outperform locale matching on average, while locale-specific generation helps on culturally divergent questions. A stress test against an SFT-aligned survey model shows competitive performance using less than 3\% of the training data. These results position preference reconstruction as a lightweight, externally verifiable alternative for survey-based population alignment. Code is available at https://github.com/bingchen-wang/P2P.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37859

Seq@K: Evaluating Language Models Under Sequential Feedback

Thomson Yen, Gilbert Yang, Naimeng Ye, Minghui Chen, Dong Xia, Tianyi Shen, Yechan Jeon, Yaqin Chen 等 11 位作者

原文摘要

Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K, a natural evaluation protocol that measures whether a model can solve a problem within K sequential attempts, provided feedback after each previous failure. Unlike multi-turn agentic benchmarks that examine long-horizon planning, Seq@K isolates and formalizes the core capability of refinement from feedback. We evaluate Seq@K on a suite of 7 benchmarks and 16 frontier models, and show that Seq@K reveals a materially different model-selection landscape: under Seq@K, (1) model rankings often differ, (2) the Pareto frontiers admit more efficient configurations and (3) the gains from choosing the optimal model configuration can widen or shrink relative to those of Pass@K. We further show that analyzing model trajectories under Seq@K helps characterize iterative refinement behavior, such as the rate at which models address issues raised in feedback, or how rigidly they hold onto their own answers. Finally, we study how the nature of feedback affects models' iterative refinement, showing that practitioners must carefully design and benchmark the feedback loops of iterative agentic systems. Together, these results establish how Seq@K offers a more faithful metric for intelligent systems that typically operate in such feedback loop, and the necessity to consider Seq@K in evaluating models for these systems.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37851

Evaluating and improving AI agents for sequencing protocol understanding

Chi-Lam Poon, Michael Goneos, Zezheng Song, Xi Chen

原文摘要

Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity. Switching the underlying language model produced larger average performance differences than switching agent harnesses, with a statistically significant difference only for molecular-state reconstruction. Additional knowledge improved oligo-family recovery in a small pilot without improving mean molecular-workflow scores. Autonomous accumulation of procedural rules and cross-protocol examples showed non-monotonic validation performance and no mean held-out molecular-workflow improvement in the tested trajectory. These findings highlight the need for more controlled and verifiable approaches to scientific reasoning about molecular processes in complex experimental protocols.

cs.AI · q-bio.GN

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.11087

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li, Jost Tobias Springenberg, Kevin Frans, Sergey Levine

原文摘要

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37849

Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening

Kevin Yandoka Denamganaï

原文摘要

AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behavioural test: a partner that uses a code reacts to the exact wording of a message, whereas an uninvolved agent placed in its seat does not. Partner--Outsider Positive Listening (PoPLi) is the difference between the two agents in how much their action changes when the message is reworded with its meaning kept, and it is computed after the fact by replaying logged prompts. In a simulated market with five conditions (no collusion, a joint reward with neutral messages, the same with an openly stated intention, a covert first-letter code, and the code with a stated intention), PoPLi is between 0.48 and 0.59 whenever the code is present (95% intervals all above 0.29) and between -0.10 and -0.01 without it. Message-only monitors did not separate the conditions: one reading the speaker's messages answered "no" in all 50 markets, and one reading every seller's messages flagged 9 of 10 markets with no collusion. PoPLi detects the use of a private channel, not collusion as such, and it cannot detect collusion through incentives alone or codes carried by meaning.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37843

Where the Error Lives: Spectral Representations of Learned Kohn-Sham Hamiltonians

Fang Sun, Hekai Cheng, Ruoyan Li, Yuanzhou Chen, Wei Wang, Jason Cong, Yizhou Sun

原文摘要

Kohn-Sham density functional theory (DFT) is the standard method for computing the electronic structure of molecules and materials, but its self-consistent-field (SCF) iterations make it expensive for large systems and high-throughput screening. Machine-learned Hamiltonian models offer a shortcut: an equivariant network predicts the Kohn-Sham Hamiltonian matrix in one forward pass, and diagonalizing the prediction yields orbital energies, the HOMO-LUMO gap, molecular orbitals and the electron density. These models are trained to match the reference matrix entry by entry, yet a small entry-wise error does not guarantee accurate eigenvalues or eigenvectors. Two physics-informed alternatives go partway: a recently proposed wavefunction-alignment loss adds a spectral penalty without diagonalizing the prediction, and matching the electron density of the diagonalized prediction supervises it directly. Neither is complete: by representing the prediction error in the eigenbasis of the reference Hamiltonian, we show that each sees only part of the error, and that shifting the predicted orbital energies leaves the electron density exactly unchanged. The same analysis identifies a complete training signal: the cumulative local density of states (cumulative LDOS), the number of electrons at each point in space with energy below a given threshold. The cumulative LDOS is a single physical observable that contains the electron density as a special case, responds to every component of the error, determines the Hamiltonian uniquely, and yields gradients that do not vanish for large orbitalenergy errors. Fine-tuning three Hamiltonian networks on QH9 in this way, which we call FermiScope, reduces the HOMO-LUMO gap error without increasing the element-wise error. The gains carry over to out-of-distribution and molecular-dynamics splits, where the wavefunction-alignment loss helps less.

physics.chem-ph · cs.AI

查看论文
arXiv ↗PDF ↗