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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 17:47 — 2026-11-09 17:47（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 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
版本更新 · v2arXiv:2605.07600

Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators

Tsuyoshi Okita

原文摘要

Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify which concepts causally contribute to a correct answer, as the observed association may be spurious, driven by confounders such as problem difficulty. We propose CIKA (Causal Intervention for Knowledge Activation), a framework that uses the LLM itself as an interventional simulator: a prompt sets the concept state to ``mastered'' and the correctness change estimates the causal effect. We formalize this quantity as an Interventional Capability Probe (ICP), which diagnoses whether the LLM can use a given concept -- distinct from merely possessing knowledge. Because the intervention exogenously sets the concept state independently of problem difficulty, ICP separates confounding that observational methods cannot. On 67 screened problems, the ICP of the top-ranked concept (+0.219) is significantly larger than that of the negative control (+0.039; paired $t$-test, $p < 10^{-6}$, Cohen's $d = 0.86$), confirming that the probe discriminates causally relevant concepts from irrelevant ones. Analysis of 601 Omni-MATH problems further shows that solved problems have 6.1$\times$ higher ATE than unsolved ones (0.338 vs. 0.055), confirming that ICP is predictive of problem-solving success. With a 7B-parameter LLM whose weights are entirely frozen, CIKA achieves 69.7\% on the contamination-free Omni-MATH-Rule benchmark and 64.0\% overall, compared to 60.5\% for o1-mini, and 97.2\% on GSM8K, 46--50\% on AIME 2024--2026, and 46.2\% on MathArena. The Causal Knowledge Activation component contributes 33.8\% of correct answers on problems where the base model alone fails, demonstrating that the LLM already possessed but had not activated the requisite knowledge.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21856

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation

Yifan Lan, Yuanpu Cao, Hanyu Wang, Lu Lin, Jinghui Chen

原文摘要

Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious model publishers who use evasive, or indirect, contamination strategies, such as paraphrasing benchmark data to evade existing detection methods and artificially boost leaderboard performance. Current approaches struggle to reliably detect such stealthy contamination. In this work, we uncover a critical phenomenon: a model's generated reasoning steps actively mask its underlying memorization. Inspired by this, we propose the Zero-CoT Probe (ZCP), a novel black-box detection method that deliberately truncates the entire Chain-of-Thought (CoT) process to expose latent shortcut mappings. To further isolate memorization from the model's intrinsic problem-solving capabilities, ZCP compares the model's zero-CoT performance on the original benchmark against an isomorphically perturbed reference dataset. Furthermore, we introduce Contamination Confidence, a metric that quantifies both the likelihood and severity of contamination, moving beyond simple binary classifications. Extensive experiments on both previously identified contaminated models and specially fine-tuned contaminated models demonstrate that ZCP robustly detects both direct and evasive data contamination. The code for ZCP is accessible at https://github.com/Yifan-Lan/zero-cot-probe.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.19760

Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay

Haiyue Zhang

原文摘要

Step-level credit evaluation can conflate numerical association with ordering and branch recovery with position-selection value. We test these distinctions in ALFWorld with two independently seeded replay banks: 27,520 continuations over 172 fixed turns. At 16 continuations per arm per bank, cross-bank replay-contrast associations are Pearson 0.736 and pooled Spearman 0.330. On 30 historical failures, A-count-selected branches at confidence-/implicit-selected positions gain 8.54 percentage points over same-position factual reruns, but their 3.33-point advantage over frozen-random positions under the same alternative-selection rule remains unresolved. Numerical association alone does not establish reliable pooled ordering; branch recovery alone does not establish better score-informed position selection. Historical judge alignment is modestly positive with an unresolved archived-control increment. Same-cohort C/D information-source comparisons and a short, sparse-exposure training pilot provide scope checks; incremental hindsight training utility remains unestablished. Findings are conditional on the tested policies, intervention support and finite budgets.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34450

EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems

Yalun Wu, Qiwei Ma, Bingbing Xu, Dan Zhang, Long Bai, Boyang Wang, Jiatong Li, Zheqi Lv 等 13 位作者

原文摘要

Decentralized multi-agent systems (MAS) enable large language model agents to interact without centralized control. Agents need to adapt to other agents at test time and reuse accumulated experience to refine their interaction strategies for future interactions across cooperative, mixed-motive, and adversarial settings. However, existing approaches often develop adaptation mechanisms for particular interaction settings. This raises a central question: how can decentralized MAS support test-time adaptation and reliable experience reuse across interaction settings? We propose EvolveMAS, a unified self-evolution framework that supports experience-driven adaptation within and across episodes. EvolveMAS pairs each main agent with a dedicated MemoryAgent for test-time memory governance, which maintains isolated Structured Memory outside the main agent's reasoning context. EvolveMAS organizes adaptation into two complementary processes: Within-Episode Online Adaptation and Cross-Episode Knowledge Evolution. During Within-Episode Online Adaptation, MemoryAgent updates episodic, semantic, and working memory from interaction evidence to inform subsequent actions. During Cross-Episode Knowledge Evolution, the main agent uses memory and episode outcomes to distill reusable interaction knowledge comprising partner profiles and interaction strategies for subsequent episodes. Across five benchmarks and six evaluation configurations spanning the three interaction settings, EvolveMAS achieves the highest normalized average score of 77.2 among the compared methods. Ablations show that test-time memory governance and cross-episode knowledge reuse both improve performance. Interaction traces further illustrate how updated memory and distilled knowledge guide subsequent interactions. These results support experience-driven adaptation in decentralized MAS without updating model parameters.

cs.MA · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.34187

LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks

Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack

原文摘要

The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they cannot move beyond statistical pattern matching into abstraction or reasoning, remaining ontologically near the lower bound of pattern reuse despite producing alluringly fluent text. We test this hypothesis using conlang-like tasks. Several LLMs are given only natural-language descriptions of fictional languages that subvert prominent superficial patterns in training data by combining statistically uncommon and unattested features. Crucially, no example outputs are given. We argue that if the models exhibit rule-following behaviour, they cannot be relying solely on superficial statistical patterns; such patterns often work against the correct output. Instead, successful performance requires representations of the constraints specified in the prompt. Across three complementary task families, models systematically move in the meaning-predicted direction: they distinguish prompt exposure from instructed use, alter semantic relationships in response to novel constraints, and sometimes produce exact matches to complex translation answer keys. Although performance varies across the spectrum of models used, these results provide evidence for meaning-mediated abstraction in LLMs and refute the strong stochastic parrot hypothesis. Our work shows that, under appropriate architectural and contextual constraints, statistical learning can produce meaning-mediated abstractions, although generation remains strongly constrained by superficial plausibility. We discuss implications for model development and for understanding how increasingly abstract representations may emerge from plausible-text-generation objectives.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34435

CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance

Chenyuan Yang, Hwiwon Lee, Jongseong Kim, Yihan Yang, Dongjun Kim, Yinfang Chen, Lingming Zhang

原文摘要

Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attacker. We present CyberDual, an arena for this dual role of AI: attacker agents hide an exploitable bug in real maintenance work on widely used open-source projects, and reviewer agents try to find and repair it. Execution decides each match: we rerun the attacker's proof of concept (PoC) on the code that comes out of review. Every attack is new, and the windows can be rebuilt each quarter from the latest upstream history. Three agentic reviewers catch 85-91% of 1,088 valid attacks from six attackers. Yet when the attacker spreads the bug over real upstream commits, about one in six attack slots still ends with a working exploit after review. The strongest attacker has open weights: GLM 5.3 almost never refuses, and its attacks make up 13 of the 28 that get past all three reviewers. When they miss, Claude reviewers mostly approve the attack, while GPT-6-Sol mostly repairs the wrong code; a reviewer from a second vendor catches about two thirds of a Claude reviewer's misses. Beyond a leaderboard, CyberDual has three uses. First, PoC execution gives both sides a reward that agent reports cannot game, so its surviving attacks can train reviewers against stronger attackers. Second, it can gate a release on both scores: Claude Sonnet 5 refuses one in five attack slots, yet attacks about as well as GPT-6-Sol, so refusal alone does not remove attack capability. Third, it can warn the teams behind a deployed reviewer when a new attacker crosses a threshold: GLM 5.3 in Claude Code already gets an exploit past Sonnet 5 in 17% of its attack slots.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.18451

CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging

Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn

原文摘要

In medical imaging, one frozen foundation encoder is often reused for many tasks. The encoder is usually chosen by the area under the receiver operating characteristic curve (AUROC) of a head trained on its features. The AUROC does not measure whether the encoder separates positive from negative images in its feature space. Chance-calibrated neighborhood discordance (CANDOR) measures this separation without training a head. Among images acquired the same way, a positive image is discordant when its k nearest negatives are more similar to it on average than its k nearest positives are. The discordance rate D is the share of discordant positives. When the neighbors come from positive and negative candidate sets of equal size, D has the chance level 1/2 for features without information about the label. With unequal candidate sets, all 11 chest encoders have rates above 1/2 (0.732 to 0.927) on the 12 chest findings of MIMIC-CXR and CheXpert. These rates increase as the finding becomes rarer. With equal sets, the same encoders have rates below 1/2 (0.277 to 0.463). On the chest test split, linear heads miss 0.301 of the discordant positives and 0.165 of the other positives. Across 22 encoders, 605,443 images, and 8 tasks in 7 domains, the best encoder of every task has a rate below 1/2. Because computing D takes one forward pass per image, a hospital can compare candidate encoders before it trains any head.

cs.LG · cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34386HF 社区推荐

ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

Haojin Wang, Yangzhen Wu, Zeyi Chen, Jian Xie, Jiaying Ye, Lili Meng, Shuyun Tang, Shangding Gu 等 9 位作者

原文摘要

Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-driven post-training is a central part of that loop, yet existing evaluations measure it on a single benchmark, where an agent selects from a static pool or distills a stronger model to push one score up in one run. Real post-training is multi-domain, and a gain in one domain has to be weighed against a regression in another. We propose ParetoRSI-Gym, in which an agent searches for data, curates it, trains, reads back per-domain results, and repeats, with everything but the data held fixed: the initial LLM, the five domains (math, code, finance, medicine, science), the toolset, and the SFT pipeline. Generalization benchmarks in each domain separate capability gains from overfitting to the scores the agent optimizes against. Across three agent systems, three base models, five rounds and multiple seeds, the strongest system, Claude Code with Opus-5, raises the generalization scores of its proxy-best checkpoint by 9.2% relative to the starting model (+2.3 absolute points), averaged with equal weight over three base models and five domains, with a single-domain relative gain of up to 63% (medicine on Ministral-3-3B). Further analysis shows that the harness matters as much as the model it drives, and that each agent keeps a unique data selection strategy. We see our work as a step towards evaluation of RSI systems in real-world machine learning engineering.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34298HF 社区推荐

Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

Zhenning Shi, Liang Pang, Yongqi Li

原文摘要

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic operations through markedly different model-facing representations. We study whether these representational differences change agent behavior when executable capabilities are matched. We introduce Matched Interface Comparison and Analysis (MICA), which renders MCP and CLI from a shared semantic action contract and routes decoded actions through the same runtime. Across six models and three interactive environments, matched interfaces produce substantial differences in task performance and interaction cost. These effects extend beyond surface validity to semantic action selection, failure pathways, and recovery. Matched-state probes localize sensitivity to capability presentation, realization, and feedback. Paired natural trajectories reveal structured divergence in 94.3% of 2,004 episodes and show that early differences propagate through subsequent interaction. This analysis identifies interface realization as a direct intervention boundary. We therefore introduce Decoupled Action Realization and Targeted Repair (DART), which preserves validated semantic commitments while repairing interface-specific realization. DART improves benchmark score in all six evaluated settings by up to 9.0 points and reduces MCP token cost in all three environments by up to 27.1k tokens per task. Together, these results establish interface representation as part of the closed-loop decision environment shaping agent behavior.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33624HF 社区推荐

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Yue Huang, Yanbo Wang, Lichi Li, Yuanyuan Chen, Andreas Haupt, Xiaonan Luo, Zheyuan Liu, Jihye Choi 等 18 位作者

原文摘要

Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive self-improvement. Ten frontier models act as training agents, each starting from NVIDIA Nemotron 3.5 Lightning 30B-A3B Base. During a six-day first stage, each agent has 1,000 GPU-hours and $300 in API credit on a shared 64-GPU cluster, independently selecting data, implementing training procedures, and choosing checkpoints. We evaluate their models on 20 benchmarks and through blind human evaluations. All ten agents produce working assistants, with the strongest model, trained by GPT-6 Astra, closing a median of 76% of the base-to-Instruct gap across 12 capability benchmarks. Its human-preference rating is also close to NVIDIA Instruct after statistical adjustment for answer length and formatting. In Stage 2, each agent receives the comparison records and votes involving its Stage 1 model and is given three additional days for further training. Using NVIDIA Instruct as a common reference across the two evaluation rounds, we observe an improvement from Stage 1 to Stage 2 in the style-adjusted relative rating of eight of the ten models. We show that benchmark gains were modest, with no clear link to preference gains, while some agents encouraged longer responses and one model showed increased harmful compliance on StrongREJECT. RSI Arena provides an auditable setting for studying how human feedback can guide autonomous model development. It takes a step toward recursive self-improvement with human feedback (RSIHF), in which people help define what improvement means for the AI systems they use.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33245HF 社区推荐

AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science

Atharva Naik, Vivek Chari, Pol Llado, Daniel Fried, Carolyn Rosé, Benjamin Van Durme, Sam Thomson, Justin Svegliato

原文摘要

Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration, unsound validation, coding bugs, and poor use of a fixed budget (re-running the same exploratory data analysis and baseline models in every attempt). We propose AdaPRA to address these issues: a persistent coding agent harness that accumulates knowledge across attempts on the same task, with rubric-guided process supervision that identifies and corrects errors. Our process reward agent audits the agent's trajectory and workspace by executing checks, and adapts its rubrics to each task. We find that rubrics seeded from easier tasks generalize to harder tasks, with rubric adaptation further improving performance. With five attempts per task, AdaPRA improves an 80B Qwen model's leaderboard percentile by 24.5 points on DSPredict-Easy and 14.8 points on DSPredict-Hard while reducing process errors. We also show that supervision with rubrics mined from one base model's runs improves another (DeepSeek-V3.2), and that AdaPRA beats DataPRM, a competitive PRM for data science. We also share our code for reproducibility.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32177HF 社区推荐

$Ψ$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model

Khai Loong Aw, Klemen Kotar, Baihan Zhang, Yifan Liu, Lilian Chen, Atlas Kazemian, Rahul Venkatesh, Daniel Yamins

原文摘要

Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabilities often remain separated across specialized models, limiting how they can be composed and jointly adapted to a task. We introduce $Ψ$-0.6, a unified vision-language world model that adaptively composes perception, language, geometry, and simulation within a shared reasoning process we call streams of thought. These streams interleave images, text, and explicit representations of geometry and motion, all of which the model can generate and interpret through a shared token interface. $Ψ$-0.6 surpasses leading open-weight models zero-shot on multi-view spatial reasoning, with further gains from reasoning through geometric intermediates. It also supports counterfactual simulation: generating and interpreting imagined scenes to determine, for example, whether moving an object would obstruct a pathway. Reinforcement learning from task feedback jointly optimizes the selection, generation, and use of intermediate representations, improving visual question-answering accuracy with gains that transfer to unseen benchmarks. $Ψ$-0.6 offers a path toward adaptive physical reasoning -- not only predicting the physical world but also choosing the representations through which to reason.

cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32046HF 社区推荐

Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?

Yepeng Liu, Shengmai Chen, Xuandong Zhao, Chengzhi Liu, Dawn Song, Xin Eric Wang, Yuheng Bu

原文摘要

Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks. However, TTT introduces additional computational cost for online weight updates during the discovery process, making computational efficiency an important consideration when scaling to larger models. This motivates us to explore an efficient \emph{test-time adaptation} method for scientific discovery. We introduce \emph{Test-Time Memory Evolution} (TTME), a plug-and-play test-time adaptation method, as an alternative to TTT. TTME continually updates the external memory by distilling the experience to guide subsequent discovery without updating model weights. To have a clean comparison, we evaluate TTME and TTT under the same discovery framework, replacing only the test-time adaptation method. Our evaluation shows that TTME outperforms TTT on all five mathematical tasks, while reducing computational cost by $82.8$-$84.6\%$ in FLOPs and $47.7$-$58.4\%$ in runtime. These results establish TTME as an effective and computationally efficient alternative to TTT in the evaluated discovery settings.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.15351HF 社区推荐

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning

Md Khairul Islam, Zeyu Xia, Adam S. Bolton, Judy Fox

原文摘要

Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed across heterogeneous instruments. We identify this coordinate mismatch as a structural limitation in cross-instrument representation learning, and propose OmniSpectra, a wavelength-native foundation model for spectral representation learning: a continuous-coordinate masked autoencoder that discards the integer pixel indexing of sequence modeling. Mapping physical coordinates to a logarithmic basis turns the multiplicative scaling induced by cosmological redshift into a uniform additive shift. In continuous rotary position embeddings, this shared shift cancels from relative token distances rather than producing grid-dependent positional distortion. We further counter the spectral bias inherent to implicit neural decoders with a physics-grounded, resolution-gated Fourier decoder that provides anti-aliasing. Pretrained on eight surveys and benchmarked against seven baselines, our model reaches state-of-the-art performance with only 12.2M parameters while outperforming substantially larger models, indicating that encoding physical structure can substitute for parameter scale.

astro-ph.IM · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.30435HF 社区推荐

Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models

Taewhoo Lee, Minju Song, Jungwoo Park, Chanwoong Yoon, Junha Jung, Hyeon Hwang, Sanghoon Lee, Minbyul Jeong 等 9 位作者

原文摘要

Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack search-state awareness, i.e., the ability to recognize what information has been obtained and what remains missing, leading to hallucinated reasoning and prematurely terminated search. To address this limitation, we propose Self-Assessment Reinforcement Learning (SARL), a reinforcement learning framework in which models learn to recognize their own search state during training and improve their search behavior accordingly, without requiring additional assessment at test time. SARL achieves this through a dual reward design that captures the corrective effect of each assessment while penalizing excessive reliance on it, jointly encouraging effective and efficient search trajectories. Under this setup, SARL achieves a 24.3% relative improvement over the strongest baseline, with average gains of 35.9% on multi-hop reasoning and 27.9% on deep research benchmarks against the strongest per-benchmark baselines. SARL further surpasses methods built on auxiliary supervision or multi-agent coordination, despite operating as a standalone RL framework with no inference-time scaffolding. Beyond final performance, SARL maintains training stability under extended search horizons, a regime where existing methods consistently degrade, enabling sustained gains as task complexity grows.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.29927HF 社区推荐

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun, Naicheng Yu, Jiawen Gong, Jingyan Shen, Huan Zhang

原文摘要

A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure mismatch, where the benchmark difficulty distribution differs from the intended difficulty distribution, and coverage gaps, where uncovered regions along the difficulty axis prevent benchmarks from detecting meaningful localized training progress. We propose two diagnostic metrics that capture these two failure modes and provide rigorous theoretical guarantees. Empirically, we analyze 25 popular benchmarks spanning 7 domains using carefully estimated item difficulties. Our results show that many benchmarks implicitly overweight certain difficulty regions, so their leaderboard conclusions should be interpreted with caution; others leave substantial portions of the difficulty axis uncovered, limiting their ability to monitor the model improvement process. Finally, we turn diagnosis into action by introducing BenchFill, a simple difficulty-targeted item rewriting algorithm that effectively reduces local coverage gaps.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.24520HF 社区推荐

HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory

Junming Zhang, Rubin Wei, Xu Cheng, Hao Sun, Jiarui Wang, Ruoxi Cheng, Xiquan Wang, Peisong Wu 等 10 位作者

原文摘要

In long-term interactions with large language model (LLM) agents, users reveal habits through their choices and actions. These habits capture implicit user information that agents must infer across conversations. However, individual observations may provide only partial evidence about a habit or when it applies. Retaining past interactions alone does not ensure that agents can infer habits and apply them appropriately. We introduce HABIT-Bench to evaluate how well agent memory systems infer habits from weak evidence and apply them to later requests. We construct synthetic user histories from task-oriented dialogue data and controlled habit graphs. The histories span hundreds of sessions across food, finance, software, and travel. Four-choice tasks assess agents' ability to infer user habits and apply them appropriately. They include temporary exceptions, changes in habits, and suggestions that users have not accepted. Sampled tasks undergo independent human review. We evaluate eight memory methods with Qwen3-235B-A22B and GLM-5.3-Flash. The best-performing memory method achieves 33.61\% macro accuracy across the four domains. Performance remains limited even when annotated evidence is supplied directly. These results expose a persistent gap between access to past interactions and the ability to infer and appropriately use user habits.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.22990HF 社区推荐

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas

Haoming Li, Defu Cao, Xu Hu, Yingtao Luo, Yiyang Wang, Xianghe Xu, Jiashu He, Wanting Jiang 等 26 位作者

原文摘要

Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving the person who asked. We introduce PersonaCUABench, which holds 74 tasks across 11 domains fixed and varies only who asks. A persona agent, playing one of 44 personas in four groups, rewrites each instruction in that user's own words and answers the CUA's questions, while the CUA sees only the dialogue, never the profile or the original instruction. Across nine backbones (3,330 runs), mean task completion falls by 36% relative to the original requests. The losses have two sources: in 59.9% of cells that lose points, the agent engages with what the user asked for and still gets it wrong, and 11.2% are stops the user requested that the checker scores as failures. Even when a persona request is fully completed, the user gives the top satisfaction rating in only 62.7% of cells, against 84.1% for the original requests. CUAs should therefore be evaluated not only on task completion but also on whether they meet the requirements and constraints users express. Code: https://github.com/MatrAIx-ai/PersonaCUABench. Project page: https://matraix.ai/research/persona-cua.html

cs.HC · cs.AI · cs.CY · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.22684HF 社区推荐

AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents

Liqin Ye, Rongzhi Zhang, Xin Liu, Zheng Li, Yuan He, Qingyu Yin, Priyanka Nigam, Chao Zhang

原文摘要

Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) forecasters often begins with preassembled evidence at a single prediction date, leaving evidence acquisition outside the learning loop. We introduce AlphaBet, an agentic reinforcement learning (RL) framework that trains a single LLM policy to search, reason, and report probabilities across multiple pre-resolution dates. Each dated forecast is scored by a proper scoring rule against the eventual outcome, allowing one resolved event to supervise decisions under different information states. We decompose forecasting regret into an evidence-acquisition gap and a probability-reporting gap, and show that Group Relative Policy Optimization (GRPO)'s standard-deviation normalization can distort the reporting target under multi-class proper scores. On GLM-4.5-Air, AlphaBet reduces the Brier score from 0.731 to 0.626 on Forecast-Dojo and from 0.612 to 0.528 on FutureX. Controlled ablations attribute these gains to multi-date training and show that they come from improvements in both information acquisition and probability reporting. Our empirical results validate that GRPO's std normalization degrades proper-scoring-rule performance while leaving top-outcome accuracy largely unchanged.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.21240HF 社区推荐

Representation Redistribution in Sparse Autoencoders

Ziye Mei, Haotian Ma

原文摘要

Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying request can redistribute activity across them. A feature change observed on one transformed prompt need not recur, and even a recurring change need not affect a downstream computation. We introduce the redistribution sensitivity score (RSS), which identifies large feature responses that recur in a consistent direction, and evaluate the resulting supports on variants excluded from selection. Across 27 pretrained SAEs spanning eight language models, the tested prompt transformations produce a reproducible redistribution profile on these excluded variants. We then separate recurring representation change from signed readout contribution and decision failure. For a fixed linear readout, an exact decomposition shows how response magnitude, readout coefficients, directional alignment, and the clean margin determine downstream consequences. In two frozen safety readouts, combining RSS support erosion with the full clean margin yields recurrent failure AUROCs of 0.935 and 0.958 using median supports of 20 and 19 features, compared with 0.965 and 0.964 using full erosion. RSS therefore provides a way to identify recurring sparse representation changes and quantify their contribution to a downstream readout without equating representation change with failure. Code is available at https://github.com/OpenSAE/Redistribution-Sensitivity-Score

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.21143HF 社区推荐

CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models

Yingzhuo Deng, Chong Li, Bingxin Liu, Yi Shu, Tianyu Peng, Can Xie, Siyao Song, Shuo Ren 等 9 位作者

原文摘要

Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenizer and decoder. CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, followed by deterministic expansion back to the original speech-token space before synthesis. On bilingual speech-dialogue benchmarks, CoSTA achieves approximately $1.7\times$ expanded speech-token generation speed, lower full-response latency, and higher throughput while preserving response quality. Analyses show more sustained interaction under limited budgets and a practical trade-off among compression, decoding efficiency, and quality. Further experiments demonstrate cross-architecture transfer and complementarity to low-rate tokenization.

cs.CL · cs.AI · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.20832HF 社区推荐

Amortizing Sequential Experimental Design in Reasoning LLMs

Anita Kriz, Antonin Berthon, Nicolás Astorga, Mihaela van der Schaar

原文摘要

Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks. We study how to amortize sequential Bayesian experimental design (BED) into an LLM by explicitly training the reasoning that guides action selection using information-gain rewards. Our approach specifies the experimental generative model independently of the LLM's own beliefs, allowing us to optimize expected information gain under a model of our choosing. We investigate the design choices for amortization, including alternative generative-model constructions, reward estimation, hypothesis-space specification, multi-step objectives, and computational costs relative to training- and inference-time BED baselines. On Twenty Questions, the resulting policies improve information acquisition and task performance, outperform inference- and training-time BED baselines at substantially lower computational cost, and generalize to unseen categories. We further demonstrate positive transfer from Twenty Questions training to Medi-Q, a real-world clinical dialogue benchmark. These results suggest that information gathering can be learned as a generalizable reasoning skill in LLMs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16238Google Research

Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search

Sarah Martinson, Michael P. Brenner, Martyna Plomecka, Brian P. Williams, Nicholas G. Reich, Zahra Shamsi

原文摘要

Probabilistic forecasting of infectious diseases is crucial for public health monitoring and preparedness but has historically relied on labor-intensive manual model curation by expert modeling teams. Bespoke development is an obstacle to scaling models to granular geographic resolutions or emerging pathogens. Here, we prospectively evaluate Empirical Research Assistance (ERA), an autonomous system that uses Large Language Model-guided tree search to iteratively generate, evaluate, and optimize executable forecasting software. ERA was primarily prompted with methodological approaches to implement, while in some instances it was tasked with developing forecasting approaches from scratch. In a fully prospective, real-time evaluation during the 2025-26 United States respiratory season, ERA generated methodologically diverse models for influenza, COVID-19, and respiratory syncytial virus (RSV). Aggregating a selection of these automatically-generated models yielded an ensemble that ranked first overall in official Centers for Disease Control and Prevention (CDC) post-season evaluations and outperformed the gold-standard CDC forecast ensembles across all three pathogens in a real-time prediction challenge. Additionally, ERA successfully navigated data-scarce scenarios for RSV. Controlled retrospective ablations allowed for additional explorations of the impact of optimization target and instruction-following on forecast accuracy. Preliminary experiments indicate that ERA's search optimization metric influences behavior of output forecasts, and using higher-tier language models in-search improves predictive performance. By autonomously generating interpretable code that creates epidemiologically relevant predictions, this framework provides a path toward rapidly scaling high-quality disease forecasting.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.19068Apple ML Research

先规划还是先检索？工具发现架构的规模研究

Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

Mingfei Zhang, Amit Surana, Ziauddin Majid, Chenxi Wang, Michael Xu

AI 速读 基于摘要

在ToolBench上系统比较Retrieve-then-Plan与Plan-then-Retrieve两种工具发现范式，发现二者优劣随查询复杂度呈现交叉。

cs.AI · cs.IR

arXiv ↗PDF ↗
查看原文摘要

Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate nearest-neighbor search. We study an alternative Plan-then-Retrieve (PtR) paradigm in which the LLM first generates Abstract Tool Stubs (hypothesized function signatures describing needed capabilities) which then serve as retrieval queries against the registry. Evaluating on ToolBench (46,984 unique API endpoints, 50 categories) across single-tool (G1), intra-category multi-tool (G2), and cross-category multi-tool (G3) query subsets, we find a clear complexity-dependent crossover: RtP outperforms PtR on single-tool queries while PtR outperforms RtP on multi-tool queries. This crossover holds at every retrieval budget (k=1 to 20), is robust across registry sizes from 1k to 47k APIs, and is consistent across model families (Gemini 2.5 Flash and gpt-oss-120b). We characterize a stub-hallucination failure mode (the LLM invents plausible but non-existent API names) that acts as a double-edged sword: on simple queries PtR's stubs abstract away proper-noun signals that RtP matches directly, yet on complex queries the same mechanism decomposes multi-faceted intent into functional sub-needs. We further analyze token overhead and show that PtR's extra discovery call roughly doubles inference cost, which pays off on multi-tool queries but hurts on single-tool ones, motivating complexity-adaptive routing as a practical direction, one that can be driven by a zero-cost signal already present in the pipeline (RtP's top-1 retrieval score).

新论文 · v1arXiv:2610.15750Google Research

Google Earth AI 地理空间推理智能体：能力与系统性评估

Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation

Noam Slonim, Aviv Slobodkin, Gil Fidel, Gal Moshitch, Mimi Sun, Lily Mihalkova, Joydeep Paul, Per Bjornsson 等 37 位作者

AI 速读 基于摘要

介绍由 Gemini 驱动的 Google Earth AI 地理空间推理智能体 GRA，并发布两个基准，系统评估其工具与智能体编排的贡献。

cs.AI

arXiv ↗PDF ↗
查看原文摘要

Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA), a Gemini-powered research system that combines geospatial data sources, foundation models, and tools to answer questions about our planet. GRA organizes these into modular domain skills and pairs them with upfront geospatial planning to decompose complex queries into multi-stage workflows. Evaluating such systems is hard: real-world problems admit multiple valid workflows, require data discovery across large catalogs, and rely on evolving ground truth. We introduce two benchmarks and release their development splits. GeoExpertQueries poses complex analytical problems grounded in practitioner use cases and refined by geospatial experts; each is paired with a consensus golden workflow from three independent experts and scored by a human-validated, tool-agnostic autorater. GeoKTools consists of templated queries with deterministic reference solvers that systematically vary the number of required tool types. We also use two external benchmarks, CBGB and UnivEARTH; the latter we find to be saturated. To isolate the contribution of GRA's tools and its agentic orchestration, we compare four configurations, each with Gemini 3.1 Pro and 3.8 Flash: a standalone LLM, the LLM with basic tools, the LLM with GRA's skills and tools but without its upfront planning and execution guidance, and GRA itself. With at most basic tools, an advanced model recovers much of the answer on templated queries but satisfies only a small fraction of the expert workflows on open-ended problems; GRA performs well on both. The largest step comes from GRA's skills and tools; on open-ended problems, its planning and execution guidance add a further gain with Gemini 3.8 Flash, letting Flash match or exceed Pro at lower cost.

版本更新 · v2arXiv:2610.01892Apple ML Research

基于选择的结构化推理：迈向高效多模态搜索智能体

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Feiyu Gavin Zhu, Xiaoyu Zhu, Jiqi Yang, Rui Yang, Arnab Kumar Mondal, Yancheng Wang, Xinke Deng, Jean Oh 等 12 位作者

AI 速读 基于摘要

将多模态智能体的开放式推理改为从预设自然语言候选集中选择，以提升推理效率并保持任务表现。

cs.LG · cs.AI

arXiv ↗PDF ↗
查看原文摘要

Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from these reasoning candidates based on their likelihoods given the current context, without requiring an auxiliary task head. Using pre-specified reasoning traces enables parallel scoring, where teacher-forced prefilling computes token likelihoods concurrently within and across candidates using a shared context KV cache. We evaluate SSR on seven multimodal search benchmarks using 2B and 4B models. Across multiple reinforcement learning objectives and supervised fine-tuning, SSR delivers significant efficiency gains without sacrificing task performance. SSR achieves an average success rate competitive with leading search agents of the same scale, while reducing per-turn reasoning latency by over 90% and total per-question model inference latency by 28-54%. Project page: https://zfy0314.github.io/ssr-webpage/.

版本更新 · v3arXiv:2504.12110Google Research

面向地球观测的LLM智能体

Towards LLM Agents for Earth Observation

Chia Hsiang Kao, Wenting Zhao, Cheryl Lam, Aarush Umap, Shreelekha Revankar, Samuel Speas, Snehal Bhagat, Rajeev Datta 等 13 位作者

AI 速读 基于摘要

作者构建了基于NASA地球观测文章与Google Earth Engine的编码基准UnivEARTH，发现零样本LLM智能体在地球观测问答上准确率仅40.0%，使用Reflexion后提升至约60%，但仍仅略高于随机水平。

cs.AI

arXiv ↗PDF ↗
查看原文摘要

Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. In this work we ask: Are AI systems ready for reliable Earth Observation? To answer this, we introduce UnivEARTH, a coding benchmark of 408 yes/no questions from NASA Earth Observatory articles across 7 various topics and over 15 satellite instruments and sources. Using Google Earth Engine API as a tool in a zero-shot setup, LLM agents achieve an accuracy of 40.0% where the code fails to run over 44% of the time. To better understand LLM agent behavior, we also analyze the impact of using the JavaScript API versus Python and the effect of providing documentation. Furthermore, we find that using a Reflexion framework significantly reduces errors: Claude-4.5-Sonnet, Gemini-2.5-Pro, and GPT-5 accuracies rise to around 60%. However, these results remain only marginally above random chance. Taken together, our findings identify significant challenges to be solved before AI agents can automate earth observation, and suggest paths forward.

新论文 · v1arXiv:2610.30161HF 社区推荐

TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents

Krishanu Adhikary, Prashant Devadiga

原文摘要

Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, such as obtaining a closure quote before closing a deposit. Adapting models to this domain requires measuring how well they follow the procedure, before and after training. Benchmarks usually judge only the records left at the end of a conversation. Many required steps, however, leave the records unchanged, so an assistant that skips them can still be judged successful. We present TauIndianBankBench, an action-oriented benchmark of 1,000 Indian retail-banking tasks where an assistant helps a simulated customer. Besides the final records, it checks that the assistant took every required step and made no unrequested change. For every model, 6.5-12.0% of sessions are judged successful when only the final records are checked, although the assistant skipped a required step or made an unrequested change. Scoring both procedure and outcome shows more accurately how well language models perform in Indian retail banking.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.26088Google Research

行星预测引擎：通过智能数据选择与基础模型嵌入实现自主地理空间预测

Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings

Evelyn Ma, Rama Kumar Pasumarthi, Kishwar Shafin, Mandar Sharma, Mimi Sun, Hamed Sadeghi, Dav M. Ebengo, Mbulayi Onesime 等 29 位作者

AI 速读 基于摘要

提出自主AI系统PPE，从自然语言查询出发自动完成多模态地理空间数据检索、融合与模型搜索，并在多个健康、风险与流行病预测任务上报告优于专家基线。

cs.AI · cs.LG

arXiv ↗PDF ↗
查看原文摘要

Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fidelity geospatial modeling. However, building predictive planetary models remains bottlenecked by a fragmented data ecosystem, requiring manual data retrieval, multimodal data curation and fusion along with iterative model selection. We present the Planetary Prediction Engine (PPE), an autonomous AI system that executes this end-to-end workflow directly from natural-language queries. PPE synthesizes multimodal datasets on the fly, retrieving spatiotemporally relevant covariates across open-web and Earth observation platforms (Data Commons, Google Earth Engine) and fusing them with geospatial foundation model embeddings (PDFM, AlphaEarth). Simultaneously, it searches over task-tailored model architecture families with automated overfitting guards. Across diverse tasks, geographies, and scientific domains, PPE consistently outperforms state-of-the-art or manually tuned expert baselines. For US spatial regression, PPE improves mean $R^2$ across 21 CDC health indicators (76.8% vs. 60.0%), FEMA national risk indices (64.9% vs. 60.0%), and the Social Vulnerability Index (66.2% vs. 58.6%). For spatial downscaling in data-scarce settings, PPE integrates localized proxies to double baseline accuracy in Nigerian food security indicators ($R^2$ of 66.1% vs. 31.5%). For epidemiological nowcasting of the 2026 DRC Bundibugyo Ebola outbreak, PPE achieves a Recall@10 of 83.3% (identifying 15 of 18 newly invaded health zones across five weekly forecasts), a +10.3 percentage-point improvement over the public state-of-the-art modeling (~73%). By combining autonomous multimodal planetary data discovery with targeted model optimization, PPE lowers the technical barrier to planetary-scale analytics, enabling rapid, customized, expert-level deployment.

首次观测 · 记录 #1软件学报:jos:7726软件学报

威胁情报驱动的多智能体Android反运行时分析方法

严欣芃, 张向宇, 范玲玲, 苏煜程, 陈森, 刘哲理, 操晓春

原文摘要

Android生态系统的开放性与碎片化使其面临着持续演进且日益复杂的安全威胁, 越来越多的恶意攻击者使用运行时分析技术来窥探应用逻辑、篡改执行流程, 从而规避Android安全措施, 加强恶意行为的持久性与影响范围. 反运行时分析(anti-runtime analysis)技术通过检测运行时分析行为, 使用户与开发者能够及时发现并采取防护措施, 保障应用完整性与数据安全. 目前, 研究人员已提出多种基于静态数据库的反运行时分析方法, 即收集已知运行时分析技术的特征情报, 将从设备中提取的信息与其进行匹配, 从而发现运行时分析技术的痕迹. 但这类方法存在“知识滞后”问题, 且分析深度和结果可解释性不足, 使其在高速迭代的运行时分析技术面前愈发乏力. 为此, 提出并实现一个基于威胁情报驱动的多智能体Android反运行时分析方法——AIntel-Agent, 该方法利用智能体技术构建动态知识库, 从Root、Hook、调试、虚拟环境、篡改这5类运行时分析技术的特征出发对设备指纹进行深度分析, 自动化、智能化地完成Android反运行时分析任务. AIntel-Agent通过智能体协作框架的设计, 提出一种从互联网实时获取威胁情报构建动态知识库的方法, 并构建循环推理机制使智能体将设备指纹与运行时分析技术的特征关联, 形成设备反运行时分析报告. 基于现实设备数据集的实验结果表明, AIntel-Agent在Android设备达到88.5%的精确率与93.9%的召回率, 其风险报告具备充足证据与可解释性, 证明了其在Android反运行时分析中的有效性.

cs.* · cs.AI · cs.MA

软件学报 · 2026 · 正式发表

查看论文
软件学报 ↗PDF ↗