跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 15:49 — 2026-11-21 15:49(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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 6,976 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.22294

Perception into Imagination: Executable Memory for World Models

Xianyao Li, Ruitong Tian, Rui Min, Fang Xu, Jing Du

原文摘要

Physical agents must use what they previously saw or touched after visibility or contact is lost. Their actions change the implications of these remembered facts. We introduce executable perceptual memory (EPM), a world-model framework that advances explicit perceptual state alongside neural latent dynamics during imagination. Its evolving read-out informs reward prediction, value estimation and policy learning. We align reward inputs with the transitions that produced them and supervise the reward head on open-loop rollouts of recorded actions. On Memory Maze $13\times13$, EPM reaches 30.37 return at 1M interactions, compared with 23.37 when the same evolving read-out informs only policy and value on a common perceptual front end: a gain of 7.00 [3.80, 10.21]. The complete method also improves control on $9\times9$ and in MiniWorld. Probes of remembered, out-of-view arrivals show stronger reward anticipation in both visual implementations. Concentration, tactile recovery and real tactile frames demonstrate complementary roles of remembered facts in imagined-policy training, motion-dependent decisions and sensory-content retention. EPM connects persistent perception to the predicted consequences and learning signals of a world model for Physical AI.

cs.LG · cs.AI · cs.CV · cs.RO

版本更新 · v4arXiv:2512.18857

CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning

Zijun Gao, Zhikun Xu, Xiao Ye, Ben Zhou

原文摘要

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final answers but provide little fine-grained conceptual signal, so models improve at pattern reuse rather than conceptual applications. We introduce CORE (Concept-Oriented REinforcement), an RL training framework that turns explicit concepts into a controllable supervision signal. Starting from a high-quality, low-contamination textbook resource that links verifiable exercises to concise concept descriptions, we run a sanity probe showing LLMs can restate definitions but fail concept-linked quizzes, quantifying the conceptual reasoning gap. CORE then (i) synthesizes concept-aligned quizzes, (ii) injects brief concept snippets during rollouts to elicit concept-primed trajectories, and (iii) reinforces conceptual reasoning via trajectory replacement after group failures, a lightweight forward-KL constraint that aligns unguided with concept-primed policies, or standard GRPO directly on concept-aligned quizzes. Across several models, CORE delivers consistent gains over vanilla and SFT baselines on both in-domain concept-exercise suites and diverse out-of-domain math benchmarks. CORE unifies direct training on concept-aligned quizzes and concept-injected rollouts under outcome regularization. It provides fine-grained conceptual supervision that bridges problem-solving competence and genuine conceptual reasoning, while remaining algorithm- and verifier-agnostic.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22291

When the World Is the Test Suite: Agentic Intelligence for the Physical World

Kaixin Li, Meng Luo, Yanlin Li, Yuchen Tian, Xiang Liu, Xiangru Jian, Yan Yang, Zhiheng Xi 等 12 位作者

原文摘要

Coding agents built to repair software now write, test, and repair programs for robots, laboratories, and industrial controllers. Unlike in software engineering, no test suite comes with the code. Whether a program works must be established by running it on a robot, in a physics simulator, or through the policies it helps to train, and such evidence is costly to obtain and can itself be wrong. As these agents take on more physical tasks, how their programs are judged matters as much as how they are written. This paper examines this emerging area, agentic intelligence for the physical world, by treating the world as the program's test suite. We organize the discussion around three questions: how agents write programs for the physical world, how these programs are tested, and how agents learn from the results. We first trace how language models for robots and software engineering agents came together, ask which software testing practices carry over to physical tests, and describe each program by where it sits relative to the actuator and by what judges it. For writing, we cover programs that act as robot policies and programs that support policy learning by producing rewards, tasks, and training worlds. For testing, we examine what physical trials cost, what traces, learned judges, simulators, and formal checks can establish in their place, and what safety requires beyond task success. For learning, we discuss how tested programs are retained as experience, in skill libraries and in model weights. Finally, we turn to benchmarks and evaluation practice and outline open challenges. Writing programs is becoming cheap, while trustworthy evidence about what they do remains costly. Progress will therefore depend on a physical counterpart of continuous integration: verification cheap enough to run often, reliable enough to trust under search, and maintained alongside the experience it validates.

cs.RO · cs.AI · cs.SE

版本更新 · v4arXiv:2503.23326

Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining

Yiyu Qian, Tim Miller, Liyuan Zhao

原文摘要

Monte-Carlo Tree Search (MCTS) is a family of sampling-based search algorithms widely used for online planning in sequential decision-making domains and at the heart of many recent advances in artificial intelligence. Understanding the behavior of MCTS agents is difficult for developers and users due to the frequently large and complex search trees that result from the simulation of many possible futures, their evaluations, and their relationships. This paper presents our ongoing investigation into potential explanations for the decision-making and behavior of MCTS. A weakness of MCTS is that it constructs a highly selective tree and, as a result, can miss crucial moves and fall into tactical traps. Full-width minimax search constitutes the solution. We integrate shallow minimax search into the rollout phase of multi-agent MCTS and use process mining technique to explain agents' strategies in 3v3 checkers.

cs.AI

新论文 · v1arXiv:2611.22288

ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents

Arunkumar V, Gangadharan G. R., S. Senthilkumar

原文摘要

Large-language-model agents now close the industrial predictive-maintenance loop, reading sensor windows, retrieving procedures and dispatching work orders. Two attack channels meet there: injected text in a retrieved document can hijack the decision, and a bounded sensor perturbation can corrupt the remaining-useful-life estimate behind it. Recent agent defenses police data provenance and tool privilege but cannot tell whether a prognostic quantity is physically plausible. ConfGuard is a reference monitor with a physics-grounded policy. Its conformal monitor tests each prediction, anchored to the asset's admitted history, against degradation physics: capped remaining life never rises and falls at most one cycle per cycle. Calibrating its threshold over whole asset trajectories lets the operator set the expected share of a clean asset's windows the running monitor escalates. A physics-policy validator checks the agent's maintenance-urgency decision against the decision a deterministic policy derives from the same interval. On all 10,196 C-MAPSS test windows the monitor cuts a covert attacker's reach on healthy assets from 0.529 to 0.046 and closes suppression of failing assets (0.151 to 0), escalating 0.027 of clean windows against a 0.05 target, while the fixed physical range it replaces leaves both attacks open. Behind a Qwen3-14B planner the composed monitors hold urgency-class injection to 0.00 and the universal sensor attack to 0.12, against 0.29 and 0.54 for a defended prompt. An adaptive attacker defeats a Mahalanobis detector on 0.504 of windows and adversarial training on 0.485. We report an attack class the projection misses.

cs.AI · cs.CR · cs.LG

新论文 · v1arXiv:2611.22286

Learning Regions of Attraction for Transverse Feedback Linearization under Controller Singularities

Abdullah Waqar Malik, Hamza Tariq, Adeel Akhtar

原文摘要

Transverse feedback linearization (TFL) achieves path following by exactly linearizing the error dynamics, but its controller is undefined on a singular set, such as zero speed for a unicycle or zero thrust for a quadrotor. The constrained region of attraction, the set of initial states from which the closed loop converges to the path without violating state or regularity constraints, determines where the controller can be safely activated. Exploiting the exact linear error dynamics, we show that this region is the largest forward invariant subset of the admissible set. We then decompose its state-constrained Zubov value function into an analytically known quadratic cost-to-go and a safety value function. We learn only the latter, by fitted value iteration without infinite-horizon trajectory labels. The resulting estimate combines an inner layer verified by interval branch and bound with a learned outer layer tested on samples. On a unicycle following a circle and a sinusoid and on a planar quadrotor, it covers on average 72.0%, 83.4% and 19.1% of the simulated region of attraction. In comparison, the quadratic cost-to-go and two physics-informed neural network (PINN) solvers of Zubov's equation cover at most 11.3%, 4.0% and 0.0% on average. Code and animations are available at https://gradslab.github.io/roa_tfl

cs.AI · eess.SY

版本更新 · v2arXiv:2610.23051

Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?

Shiguang Wu, Yaqing Wang, Quanming Yao

原文摘要

The learning algorithm view of in-context learning (ICL) studies how fixed-parameter Transformers learn from supplied examples. Language model agents extend this setting through interaction: their actions determine what evidence enters context next. We call this regime Agentic In-Context Learning (Agentic ICL). Existing studies largely depend on externally supplied contexts or reward-bearing interaction histories, while work on general tool-using agents lacks a learning algorithm view. We represent an interactive learner by its state, update, and decision rule, covering active learning, bandits, and online reinforcement learning (RL). For expressivity, we construct causal Transformers that approximate these algorithms over a finite horizon, and bound the resulting loss in return. For training, we characterize when optimizing process rewards preserves behavior that maximizes the final outcome. Distillation experiments show that Transformers can learn to execute three representative recursions. We then train models from outcome or process rewards without oracle action or state targets, as in RL post-training. Different rewards yield distinct decision policies. Improving the alignment of process supervision with outcome-optimal action preferences shifts learned decisions accordingly. Such behavioral differences persist in a pretrained language model across textual paraphrases.

cs.AI

新论文 · v1arXiv:2611.22283

Towards Physics-Constrained Rectified Flow for Climate Downscaling: What Projections Can Certify?

Arun Sharma

原文摘要

Statistical downscaling restores the regional detail behind flooding and crop stress, but diffusion and flow-matching generators can produce sharp fields that break the conservation laws of their coarse input. Physics-Constrained Rectified Flow (PC-RF) is a conditional flow-matching downscaler. Its training penalties target wind divergence, negative precipitation, and mass drift from the coarse total, and a projection after sampling removes the last two exactly. On one corrupted synthetic field with no trained network, the projection drives the Non-negativity Violation Rate (NVR) from 0.236 and the Mass-Conservation Error (MCE) from 0.184 to zero, and the penalties lower the Divergence Error (DE) by about 30%. On ERA5 the projection gives PC-RF and RF-base, the penalty-free rectified-flow baseline, an NVR of exactly zero and an MCE of zero up to float32 rounding. The penalties add no perceptual gain that we can separate from training budget or run-to-run variation. At a matched budget on 2019-2021, PC-RF has no edge over RF-base (SSIM 0.939 vs. 0.942, PSNR 31.81 vs. 31.79, CRPS 0.771 vs. 0.772). Our unprojected CorrDiff reimplementation beats both flow models on PSNR (28.38) and CRPS (1.092) on 2020, yet 45% of its ensemble-mean precipitation cells are negative. On ERA5 a sign error in the divergence operator made that penalty and DE act on a deformation-like term. The fine reference is interpolated from ERA5 and accumulates precipitation over a longer window, so the perceptual scores cannot establish downscaling skill. NVR and MCE need one pass and no fine reference, so we argue they should run first as pass-or-fail checks, with DE as a diagnostic.

cs.AI

新论文 · v1arXiv:2611.22281

SeasonRainBench: Global Seasonal Precipitation

Qiuyan Sun, Mengxuan Chen, Haoyuan Liang, Guowen Li, Zhen Huang, Jianhao Lin, Juepeng Zheng, Haohuan Fu

原文摘要

Accurate seasonal precipitation forecasts help societies prepare for drought, flooding, and crop failure months in advance. While data-driven methods have made rapid progress in weather and subseasonal forecasting, operational seasonal precipitation prediction still relies on numerical ensemble systems. These systems are computationally expensive and exhibit biases and drift that increase with lead time, motivating more efficient data-driven alternatives. Yet this transition faces three linked challenges: comparing data-driven forecasts with operational ones requires (1) a global benchmark that does not exist, scoring them requires (2) metrics that capture operational priorities beyond anomaly correlation (ACC) and RMSE, and training them must (3) rely on a single, short observational record. To address the first two challenges, we introduce \BenchName, the first such benchmark, covering monthly precipitation forecasts 1--5 months ahead. It pairs global $1^\circ$ satellite precipitation with oceanic and atmospheric predictors, includes seven operational centers, and provides 310,944 simulated months from 52 climate models for training. Beyond standard scores, we introduce two operationally motivated metrics for anomaly strength and monthly rain-belt position. To address the third challenge, we develop \MODEL, which learns from simulations what the record lacks and transfers it to Earth through three modules: SimForced aligns the climate background, SimMemory transfers a history encoder pretrained on simulations, and SimAnalog supplements Earth labels with simulated analog outcomes. Extensive experiments show that \MODEL{} improves ACC, CRPS, anomaly strength, and rain-belt position by 12.0\%, 3.6\%, 2.9\%, and 0.3\% over the strongest operational or data-driven model, opening a path from simulated worlds to Earth system prediction.

cs.AI

版本更新 · v2arXiv:2611.01467

See, Think, Use: Diagnosing Perception and Reasoning Failures in VLMs

Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai

原文摘要

We present See, Think, Use, a protocol that traces each answer of a vision-language model to perception, reasoning or the use of perception. The diagnosis shows a developer which stage to improve and directs test-time compute to the stage that fails. Benchmarks score the final answer, and an answer that rests on the image earns the same credit as a guess or a memorized prior. The protocol asks the model two extra questions per item and needs no access to its weights. A localization probe asks for a box around every instance and measures seeing, and a text-replacement probe answers from a description and measures thinking. Use is the rate at which the answer follows the model's own perception across counterfactual image pairs. The rate needs no answer labels, because the question and its prior are the same on both images. On two model families and six datasets the protocol shows that the knob that helps follows the task family. Answers follow the model's perception except on images that contradict a common prior, and asking the model to localize first repairs this failure when its boxes are right. Allocating compute by the measured stages comes close to the best uniform policy at lower cost and beats a random allocation of the same compute wherever a knob raises the short stage. We will release the code, the prompts and the per-question outputs.

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.22278

DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment

Peng Yu, Xiaoyu Wen, Zhida He, Ziyuan Zhou, Han Qi, Shao Zhang, Qiaosheng Zhang, Ying Wen 等 9 位作者

原文摘要

Ensuring robust safety alignment of large language models (LLMs) is increasingly difficult as adversarial attacks evolve and outpace alignment pipelines built on pre-collected data. Existing co-evolutionary frameworks let the defender chase a moving attacker, yet their training dynamics expose two compounding pathologies: \emph{attack strategy collapse}, where the attacker overfits to a narrow set of high-reward rewrites, and \emph{defense adversarial forgetting}, where the defender loses competence against earlier attacks as the attack distribution drifts. Existing remedies are partial: attacker-side diversity rewards score textual novelty rather than strategy novelty, and defender-side replay relies on discrete judge scores that ignore estimation uncertainty, response stochasticity, and defender non-stationarity. We introduce \textbf{\method}, a diversity-driven adversarial co-evolution framework that targets both pathologies jointly. On the attacker side, \method couples an explicit two-dimensional strategy space (risk category $\times$ attack style) with a \emph{normalized marginal coverage gain} reward, providing a bounded, non-vanishing exploration signal at the strategy layer. On the defender side, \method maintains a unified \emph{Bayesian adversarial replay pool} whose Beta--Bernoulli threat posteriors are refreshed by time decay and sampled via Thompson sampling, anchoring defender training to an evolving threat landscape. Across standard safety, automated-attacker, and general-capability benchmarks, \method improves robustness to out-of-distribution attacks while preserving general capabilities, and yields broader attacker strategy coverage.

cs.AI

新论文 · v1arXiv:2611.22272

Neural Network Path Optimization for Finding Transition States on a Machine Learned Potential

Kareem Hegazy, Eric C-Y Yuan, Anup Kumar, Dmitriy Morozov, Daniel Barter, Michael W Mahoney, Teresa Head-Gordon, Samuel M Blau

原文摘要

Transition states govern chemical reaction rates and outcomes, yet locating them remains a central challenge in computational chemistry. Double-ended search methods find transition states given reactant and product structures, but generally rely on discretized path representations developed for density functional theory, where potential energy surface evaluations are expensive. Machine learned interatomic potentials (MLIPs) dramatically reduce this cost and leverage automatic differentiation to access higher-order derivatives efficiently. We introduce Popcornn, a framework to find transition states by optimizing continuous neural network paths atop an MLIP with a parallelized adaptive numerical integrator. This combination eliminates path discretization artifacts, reduces hyperparameter sensitivity, and enables non-local optimization to overcome local features using second-order potential-energy-surface information. Popcornn consistently recovers more correct transition states than standard methods such as nudged elastic band and growing string, across MLIPs on thousands of organic reactions, establishing it as a robust, automation-ready method for high-throughput transition state search. Popcornn's infrastructure is flexible in path objective, integration strategy, and optimization algorithm, making it a practical tool and platform for investigating open questions in MLIP-based path optimization.

physics.chem-ph · cs.AI

新论文 · v1arXiv:2611.22270

Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback

Seiya Kawano, Koji Marusaki, Hirofumi Nonaka, Koichiro Yoshino

原文摘要

Patent prior-art searchers issue Boolean queries line by line, broadening to find relevant documents and narrowing until candidates can be screened. We distill 38,397 Japan Patent Office search reports into executable expert strategies, re-execute them, and evaluate generated strategies by citation recall and the smallest set containing each citation. Prompted models write valid, high-recall strategies but leave citations in sets too large to screen. We adapt a generator offline from scored rollouts in two forms: strategy-level learning from a screening-aware strategy score, and line-level learning from citation-preserving narrowing credit, which upweights the query lines keeping a found citation in a smaller set. On shared rollouts, line-level credit outperforms strategy-level scores on screening measures; iterated, it cuts the median citation-containing set from 768 to under 50 and places more citations in sets under 100 documents than experts, at lower recall. Strategy-level preference learning reaches near-complete recall; the two forms are complementary.

cs.IR · cs.AI · cs.CL

版本更新 · v2arXiv:2610.07476

Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance

Tom Kimpson, Mauricio Baker, Emlyn Graham

原文摘要

Frontier AI treaties or agreements on limiting computation require external verification; an external auditor must be able to confirm how much computation actually ran and that parties are adhering to the agreement. Analogue, off-chip measurements such as power draw provide an information channel for verification. It is unknown how well these analogue channels can constrain the amount of computation against an adversary who actively tries to subvert the audit. We derive a closed form for $β$, the largest hidden computation a power trace cannot exclude, as a fraction of the declared machine capacity. Measurements on NVIDIA A100 GPUs give $β= 1.16$ in the worst case, while an adversarial matched-energy schedule hides at least $0.41$. Analogue power measurements alone therefore constrain compute weakly. Additional restrictions granted by the threat model, such as the ability of the verifier to re-execute the declared work at an observed operating point, let the verifier push $β$ down to $0.059$ in the maximally restricted case. This gives a quantitative estimate of what analogue measurements can contribute to compute verification.

cs.CY · cs.AI · cs.CR

版本更新 · v3arXiv:2604.22774

When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR

Jin Seong, Wencke Liermann, Minho Kim, Jong-hun Shin, Soojong Lim

原文摘要

Accurate transcription of handwritten mathematics is crucial for educational AI systems, yet current benchmarks fail to evaluate this capability properly. Most prior studies focus on single-line expressions and rely on lexical metrics such as BLEU, which fail to assess the semantic reasoning across multi-line student solutions. In this paper, we present the first systematic study of multi-line handwritten math Optical Character Recognition (OCR), revealing a critical failure mode of Vision-Language Models (VLMs): over-correction. Instead of faithfully transcribing a student's work, these models often "fix" errors, thereby hiding the very mistakes an educational assessment aims to detect. To address this, we propose PINK (Penalized INK-based score), a semantic evaluation metric that leverages a Large Language Model (LLM) for rubric-based grading and explicitly penalizes over-correction. Our comprehensive evaluation of 15 state-of-the-art VLMs on the FERMAT dataset reveals substantial ranking reversals compared to BLEU: models like GPT-4o are heavily penalized for aggressive over-correction, whereas Gemini 2.5 Flash emerges as the most faithful transcriber. Furthermore, human expert studies show that PINK aligns significantly better with human judgment (55.0% preference over BLEU's 39.5%), providing a more reliable evaluation framework for handwritten math OCR in educational settings. Code is available at https://github.com/9115jin/PINK.

cs.CY · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.22263

Fidelity Regret: Measuring Simulator Misspecification in Verifiable Design

Noah Flynn

原文摘要

RLVF assumes the verifier evaluates the quantity of interest. In genetic-circuit design, a topological verifier can establish that a program is a valid circuit computing the target function, whereas ranking its physical performance requires a simulator. We measure fidelity regret, the reference simple regret incurred when a cheap simulator selects the design, over a 21,362-design combination subspace spanning 5 measured gate libraries and 3 organisms. Exact ordered-assignment checks retain positive regret in every tested cell while shifting magnitudes in both directions. Mean normalized regret is 0.369 over 72 cells and only 6 have zero regret. The discrepancy depends strongly on the reference axis: the yeast library SC1C1G1T1 has mean regret 0.113 for cytometry quality and 0.801 for growth burden, and every evaluated library--circuit-size pair has positive burden regret. Topological verification ties all valid gate assignments, while an oracle whitelist subject to retaining at least 25% of the design space leaves positive regret in 30 of 52 cells. Design-space optimization and feedback-guided search with frozen language models reach the high-regret regions; on a matched zero-regret control, additional optimization instead reduces regret. At a matched modeled-cost budget, mitigation is budget- and library-dependent. An in-sample fixed rule spending $α{=}0.34$ of the budget re-scoring top cheap-simulator designs achieves mean excess regret 0.016, compared with 0.305 for cheap-only and 0.034 for reference-only selection, improving on cheap-only in 330 of 360 cells. More broadly, any workflow optimized through a simulator or digital twin can satisfy its verifier yet perform poorly on the intended physical objective. Fidelity regret provides a transferable template for detecting this gap before optimization and comparing budget-aware remedies across scientific domains.

cs.AI

新论文 · v1arXiv:2611.22262

OfficePrism: Benchmarking Agents on Single-Domain Operations Across Enterprise Business Functions

Hanfeng Liu, Zhenyu Luo, Dongchao Zhang, Zexi Liu, Zulong Chen, Jinxin Hu, Jia Xu, Zeyi Wen

原文摘要

Broad workplace scores can mix competence within one business function with the extra cost of coordinating across functions and systems, making failures hard to localize. OfficePrism evaluates this prerequisite through 420 single-domain enterprise tasks spanning seven business functions under shared, benchmark-defined L1--L3 task-structure levels. Each task runs in a fresh environment combining a shared synthetic organization with one function-specific domain and yped state access. Our pipeline uses grounded records, business rules, and tool schemas to jointly construct a Chinese-language ticket, a hidden executable reference witness, and an expected response, followed by automated filtering and human curation. The same task set is evaluated through full-schema and search-and-dispatch packages. Across 124 model--harness--package configurations, the per-case joint natural-language-and-database pass rate ranges from 22.6% to 76.4%, with a median of 67.9%. L1 is highest in all 124 configurations, and L2 exceeds L3 in 122. Among 50 configurations sharing the same harness and model labels across both packages, search scores higher in 30, ties in one, and scores lower in 19.

cs.CL · cs.AI · cs.LG · cs.SE

版本更新 · v2arXiv:2611.07483

Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs

Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang

原文摘要

Enterprise AI agents split requests across subagents, and each handoff can drop, alter or ignore a requirement. A preregistered study on synthetic, exactly scorable tasks compares free-text, structured JSON and signed requirement-manifest handoffs: the orchestrator extracts each requirement as a verbatim quote plus a checkable predicate, code signs it and deterministically verifies the merger's decision. With Qwen3-8B (1,440 trajectories, five threats), signed manifests cut unsafe commits under attack from 69.4% to 9.0% (60.4 pp, 95% CI [51.4, 69.4]) with no detectable utility loss versus structured handoffs (S2 -0.4 pp, 95% CI [-14.2, 13.3]). Signing defeats in-transit mutation: unsigned manifests violated 79.2 pp more often than signed ones, which never did; this replicated in gpt-oss-20b and gemma-4-12b. There, without an adversary, signed manifests were descriptively slightly worse than structured handoffs (11.1% vs 2.8%; 16.7% vs 8.3%; not tested) and lost utility overall (gpt-oss-20b, all threats: -28.7 pp). On identical Qwen3-8B trajectories, the deterministic verifier caught 78.7% of violating decisions versus 59.0% for an LLM checker, and an oracle manifest removed all remaining unsafe commits, so the residual risk is in extraction. A preregistered pre-signing injection confirmed this: one adversarial line raised signed-manifest unsafe commits from 14.6% to 37.5% (Qwen3-8B), 11.1% to 63.9% (gpt-oss-20b) and 16.7% to 97.2% (gemma-4-12b), and every such commit carried a manifest corrupted before signing. Signing protects transit; extraction is the trust boundary. A testable pre-signing specification (PSE), specified after the injection results and frozen before an offline evaluation, blocked all these injected commits (fixed templates) but refused 45.8%, 11.1% and 22.2% of benign requests, changing completions by -8.3 pp, -2.8 pp and 0.0 pp.

cs.CR · cs.AI · cs.MA

新论文 · v1arXiv:2611.22252

A Visual Information Extraction System Using Multimodal Large Language Models for Scanned Cognitive and Behavioral Assessments

Enshuo Hsu, Linh Nguyen, Sunyang Fu, Heath Goodrum, Sandra Stansberry, Kirk Roberts, Hongfang Liu, Yen-Chi L. Le

原文摘要

Objective. Paper-based assessments are common in patient care, but handwriting and scanning artifacts make these forms difficult to process at scale. This study proposes a modular, multimodal LLM-based system with human oversight for extracting fields and scores. We conducted a qualitative analysis of the use of LLMs for hand-drawing analysis. Materials and Methods. The system processes cognitive assessments (i.e., MMSE, MoCA, Mini-Cog) and the NICHQ Vanderbilt Assessment using two modules: 1) a form classifier that assigns a scanned page to a form type, followed by a corresponding 2) score extractor that extracts fields and scores into a schema. A human-in-the-loop design utilizing dual-model validation engages human annotators when two LLMs disagree, limiting manual review to challenging pages only. Results. End-to-end accuracy for cognitive assessments was 88%, with most form types exceeding 90%. For the NICHQ Vanderbilt, overall accuracy reached 97.5%, with all form types above 96%. The human-in-the-loop design further improved cognitive assessment accuracy to 97.5% while reducing manual work by 63.8%. In the Mini-Cog Clock Drawing task, qualitative analysis showed that 62.3% of all extraction errors stemmed from ambiguous drawing, in which cases the LLM provided reasonable readings. Discussion. Compared to current manual data extraction, our LLM-based system reduces processing time by 10 to 20 times and costs by over 12 times. The modular design allows seamless expansion to additional form types. Conclusion. Our system provides an accurate, scalable, and cost-efficient solution for structuring data trapped in handwritten paper forms for clinical decision support.

cs.AI

新论文 · v1arXiv:2611.22250

PCGRL for Complex Platformers: Synthesizing Playable and Diverse Levels via Inflated Envelopes and Forward Curricula

Di Wu

原文摘要

Procedural Content Generation via Reinforcement Learning (PCGRL) has emerged as a promising paradigm for automated game development. However, existing PCGRL frameworks still suffer from severe exploration bottlenecks and scaling limitations when faced with long-sequence generation tasks governed by strict rigid-body rules and non-linear kinematic boundaries (e.g., platformer constraints). Consequently, traditional approaches frequently fail to maintain reliable level solvability on large-scale canvases. To address these challenges, we present a physics-aware, curriculum-guided PCGRL framework. First, we construct an "Inflated Volume Envelope" mechanism, which provides a physics-constrained representation that incorporates continuous kinematic feasibility into the discrete state space of the MDP. Second, to alleviate the sparse reward challenge induced by extremely long decision sequences, we introduce intermediate state-transition feedback and a multi-stage forward extension curriculum learning framework, enabling informative value estimation and stable credit assignment over long-horizon trajectories. Finally, to resolve the issue where deterministic policies after convergence generate highly monotonous map paths with a lack of diversity, we activate high-entropy stochastic inference during the synthesis phase, regularized by a post-hoc parallel rejection filtering mechanism. Experimental results demonstrate that our framework significantly enhances structural diversity while maintaining high physical playability across multi-scale environments. Comparative evaluations across multi-scale canvases demonstrate that our framework maintains superior convergence stability and dimensional scalability, reliably synthesizing solvable levels where traditional PCGRL baselines degrade.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.20730

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

Jihoon Kwon, Jiwon Choi, Jy-yong Sohn

原文摘要

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference costs as context length increases. While task vectors offer a promising alternative by compressing demonstrations into compact hidden-state representations, their quality has been evaluated only through downstream task accuracy. This indirect criterion provides limited insight into how to design more effective task vector extraction methods. In this paper, we posit that inference using task vectors should align their predictive distribution with that of ICL. To quantify this, we introduce $d_{\text{NTP}}$, a metric that measures the discrepancy in next-token probabilities between task vector-based and ICL-based inference. Our empirical analysis reveals that $d_{\text{NTP}}$ serves as a performance proxy, exhibiting a strong negative correlation with downstream accuracy. Motivated by this, we develop Linear Task Vector (LTV), a method designed to minimize $d_{\text{NTP}}$ via a closed-form linear mapping that estimates demonstration effects through regression. Across eight classification benchmarks and five LLMs, LTV consistently outperforms existing task vector baselines, improving average accuracy by 9.2\% while reducing inference latency. We further show that LTV outperforms the baselines on regression tasks. Moreover, we investigate the transferability of LTV across different model scales; an aspect that has remained nascent in task vector research. Specifically, we empirically show that task vectors from a larger model can enhance a smaller model's performance by 6.4\%, suggesting a new utility for extracted task representations.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22248

OAK-Mind: Zero-Training Mental Health Change Inference from Passive Sensing via Knowledge-Grounded Multi-Agent LLMs

Yishu Ji, Zhihan Jiang, Will Ke Wang, Yuang Fan, Anind K. Dey, Xuhai "Orson" Xu

原文摘要

Wearable and smartphone sensors capture behavioral signals associated with mental health, yet inferring mental health outcomes from these signals has traditionally relied on supervised models requiring labeled data and offering limited insight into their predictions. Large language models (LLMs) offer new opportunities to reason over behavioral evidence, but existing LLM-based approaches to passive sensing have largely continued to rely on task-specific fine-tuning or sensor-specific pretraining. In this paper, we introduce \textbf{OAK-Mind}, a zer\textbf{O}-training, multi-\textbf{A}gent, \textbf{K}nowledge-grounded LLM pipeline for inferring mental health changes from passive sensing data. The pipeline organizes sensing data into behavioral dimensions including sleep, physical activity, location mobility, and smartphone use, and orchestrates specialized agents grounded in mental health literature to interpret longitudinal behavioral changes. It synthesizes their assessments and applies questionnaire-based symptom rating to infer changes relative to an individual's baseline assessment with human-readable rationale grounded in observed behavioral patterns and domain knowledge. Across datasets and prediction tasks, while without task-specific training, OAK-Mind achieves comparable or better performance than the most predictive supervised baselines trained on additional labeled samples. It also demonstrate consistent improvement upon direct prompting across four tested LLM backbones. Ablation analyses support the benefits of combining behavioral interpretation with symptom rating, distributing analysis across domain-specific agents, and incorporating domain knowledge. Our findings highlight the potential of knowledge-grounded, multi-agent LLMs for training-free inference of mental health changes from passive sensing data.

cs.MA · cs.AI · cs.HC · cs.LG

版本更新 · v2arXiv:2611.20827

ProcReverser: Multi-Agent Black-Box Microarchitectural Reverse Engineering for Processor Vulnerability Analysis

Guanqi Lyu, Decheng Qiu, Guangyang Zhang, Fei Zhao, Zhaojun Lu, Jiaji He, Yongqiang Lyu

原文摘要

When processor implementation details are unavailable, black-box microarchitectural reverse engineering helps security researchers identify hardware conditions related to security vulnerabilities. However, this process requires substantial manual effort to design experiments, develop test programs, and analyze results for each processor. We present ProcReverser, a multi-agent system that automates this process. ProcReverser uses execution feedback to improve experimental plans and test programs and identifies microarchitectural properties from measurements. We develop a comprehensive suite of property identification tasks focused on hardware mechanisms relevant to Spectre-class attacks, covering speculative execution, branch prediction, memory dependence, and cache behavior. We evaluate ProcReverser on the XuanTie C910, the gem5 RISC-V O3 CPU model, and the SiFive P550. ProcReverser achieves Pass@1 and Pass@5 scores of 81.3% and 93.8%, respectively, on C910, and 83.0% and 100.0% on gem5 O3. On the SiFive P550, ProcReverser further characterizes microarchitectural properties covered by the proposed task suite. These findings highlight the potential of automated microarchitectural reverse engineering to support processor vulnerability analysis and defense evaluation.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22239

Solver-Free and Cost-Aware Online Scheduling of AI Data Center Tasks

Xin Qin, Dawei Qiu, Fei Teng

原文摘要

AI data centers receive computing tasks continuously, whereas solver-based optimization takes time to run and electricity is priced per settlement period. This paper bridges this timing gap through a solver-free online optimization rule inspired by dual decomposition. The rule assigns each task a start period upon arrival to optimize energy cost subject to operational constraints, shifting flexible tasks toward low-price periods while keeping high-priority tasks on schedule. Simulations on the A100 GPU trace (3,456 GPUs, 1,343 tasks) show that the proposed rule keeps GPU and CPU use within capacity while scheduling tasks at low cost. Compared with a multi-timescale optimization benchmark, it achieves a lower cost and, because it needs no solver, much less computation time.

eess.SY · cs.AI

新论文 · v1arXiv:2611.22238

Context Has a Price: Adding and Removing Context for LLM Coding Agents under Prefix Caching

Zerui Yang, Miaomiao Dong, Quan Xue, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents repeatedly send their conversation history to a language model. Adding useful code may reduce search, while removing old tool outputs may shorten later prompts. But do these changes reduce the cost of solving a task? We study this as a measurement problem in more than 20,000 runs of open models on SWE-bench Verified, SWE-bench and Loc-Bench. We account separately for uncached input, cached input and output tokens. Three findings emerge. First, in our main evidence-package experiments, retrieved code reduces read and search commands by 18--34%, but increases cost by 33--42% when cached input costs one tenth of uncached input, without a measurable improvement in resolution. Second, removing old observations can either save money or increase cost: the same approach saves 19--36% without a cache discount but increases cost by 38--116% with a tenth-price cache. Third, shorter prompts do not guarantee cheaper runs because agents may respond by taking more steps. We also find that concurrent experiments can share cached prefixes and distort cost comparisons. These results show why context-management methods should be evaluated using both token prices and the agent's subsequent behavior.

cs.AI

新论文 · v1arXiv:2611.22234

The Fragility of Reasoning-Importance Attribution for Pruning Language Models

Himanshu Mishra

原文摘要

Attribution-guided pruning scores components by their causal contribution and protects the important ones, and it is increasingly applied to compress reasoning language models without destroying their chain of thought. Its reliability rests on an unexamined assumption: that reasoning importance can be faithfully measured. Across four small reasoning models, we show this measurement is fragile in three ways, each of which changes pruning decisions. First, scoring final-answer tokens, the natural choice, saturates in every chain-of-thought model we test (answer-token negative log-likelihood, NLL, of $10^{-4}$--$10^{-3}$) because the model states its answer inside its own reasoning; guiding head pruning with this target costs 27.6 and 32.2 accuracy points relative to scoring reasoning tokens on the two models we power with five seeds, while perplexity barely moves and even reverses sign at 7B. Second, causal importance is not localizable to single units: single-neuron effects sit at the measurement floor, their cross-split ranking is noise, and they cancel: a group's ablation effect disagrees in sign with the summed effects of its members in 90\% of groups. Reproducible importance emerges only at groups of $\sim 100$ neurons. Third, contrastively isolated ``reasoning-specific'' importance is not separable from generic importance, and protecting it is worse than protecting raw importance. We additionally pre-registered the hypothesis that distillation-induced concentration of importance predicts the pruning cost; it is not supported, and since our grid confounds concentration with scale, we report it as unresolved rather than reversed. The result is a short set of measurement rules: score reasoning tokens, attribute at coarse granularity, and evaluate with accuracy rather than perplexity.

cs.AI

版本更新 · v2arXiv:2611.19345

Information Limits of Replay-Free Recurrent State Migration

Khizar Qureshi

原文摘要

When a recurrent model is replaced, its old state may not determine what the new model would compute from the same history. We characterize the information that must be retained before the replacement is known. For a time-invariant affine linear family, the minimum continuous causal memory for order-$k$ local migration equals the reachable dimension of a lifted coefficient system minus the information in the anchor state. A controllable $d$-state model with scalar input needs at most $kd$ additional real coordinates, even when arbitrary matrix replacement directions are revealed only after streaming. A single rank-one direction can already require all $kd$. Conditional singular values and auxiliary-bit bounds distinguish this local information law from recovery at a fixed tolerance. We also give invariant-subspace and future-output constructions. Controlled experiments compare the resulting representations. In a small language model, equal-memory cubic interpolation improves mean state fidelity over third-order coefficients but provides no meaningful predictive gain. An analytic history basis preserves useful adaptation more economically in a coupled identification task. With repeated slow poles, eight history coordinates meet normalized output error $10^{-4}$ across five fitted seeds despite substantial full-state error. Splitting the poles raises the smallest tested successful width to 64.

cs.AI · cs.LG

版本更新 · v3arXiv:2601.21760

GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs

Ruian Tie, Wenbo Xiong, Zhengyu Shi, Xinyu Su, Chenyu jiang, Libo Wu, Hao Li

原文摘要

Climate downscaling of General Circulation Models (GCMs) is an ill-posed inverse problem, as GCM outputs and reanalysis fields arise from different dynamical systems and lack fine-scale temporal pairing. Supervised methods thus rely on synthetic degradations or model-specific adaptation, limiting generalization across heterogeneous GCMs. Zero-shot diffusion posterior sampling (DPS) avoids paired supervision by combining a high-resolution climate prior with inference-time constraints from coarse GCM inputs, but faces consistency and efficiency challenges. We propose GCM-consistent Diffusion for Zero-shot Downscaling (GCD), which addresses these challenges with geographic conditioning, spectrally filtered measurement guidance, and distillation-accelerated Conjugate Gradient guidance. GCD reduces inference from 1,000 diffusion steps to 6 while maintaining consistency with the coarse GCM inputs. Across five heterogeneous GCMs, GCD achieves competitive 99th-percentile extreme-event accuracy and reconstructs plausible high-frequency tropical cyclone structures without model-specific retraining. Github: https://github.com/shawnvonbohr/GCD-Climate-Downscaling.git

cs.AI

版本更新 · v2arXiv:2611.03747

Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation

Huan Phong Thai, Thu Anh Ngoc Le, Nhu Huynh Thi Le, Nhan Huu Tran, Lenh Cong Phan Pham, Hong Nhung Nguyen

原文摘要

Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To address these challenges, Retrieval-Augmented Generation (RAG) models have emerged as a powerful solution, combining retrieval-based methods with generative capabilities to enhance response quality. In this study, we present a Retrieval-Augmented Generation (RAG) system designed to generate responses related to stock market information. The system integrates retrieval-based and generative approaches to enhance the accuracy and relevance of financial text generation. To evaluate its effectiveness, we employ the ROUGE metric, specifically ROUGE-1, ROUGE-2, and ROUGE-L, to measure lexical and structural similarity between generated and reference texts. Experimental results on a dataset of 100 stock market-related queries demonstrate high ROUGE scores, indicating strong alignment with reference documents. Additionally, we assess latency to evaluate the system responsiveness, achieving an average response time of 1.16 seconds. These findings confirm that our RAG model is capable of providing accurate and timely stock market insights, making it a promising approach for financial information retrieval.

cs.IR · cs.AI

版本更新 · v3arXiv:2512.02368

Intra-Agent Motion and Inter-Agent Relation Learning for Map-Free Trajectory Prediction

Wenyi Xiong, Jian Chen, Wenhua Chen, Ziheng Qi

原文摘要

Trajectory prediction is essential for safe planning and decision-making in autonomous driving. Map-free prediction improves deployment flexibility by removing the dependence on high-definition maps, but it also loses explicit road-topology and lane-connectivity priors. Consequently, the model must recover stable motion cues from short histories while resolving prospective interaction relations without lane-level guidance. To address these challenges, this paper proposes a map-free trajectory prediction framework centered on a novel Goal-Conditioned Expert-Routed Transformer (GCERT). A lightweight intra-agent front-end first decomposes projected historical motion features into a smooth trend and a local detail residual through a centered moving average. Component-specific residual projections transform the two signals before a causal temporal Transformer summarizes their recombined evolution. GCERT employs dual-level expert routing: edge-level relation experts generate interaction-specific messages, while node-level state experts adapt the transformation after message aggregation. Predicted motion goals update the node representations and construct prospective relative-geometry and orientation edge features before the final interaction layer, thereby conditioning attention, relation-specific message generation, and state transformation. GCERT therefore determines not only which neighboring agents should be attended to, but also what relation-specific information should be transmitted and how the aggregated node state should be transformed. The resulting representations are decoded into multimodal future trajectories and jointly optimized with trajectory-regression, mode-classification, and goal-prediction objectives.

cs.CV · cs.AI