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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 04:39 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 05:18 — 2026-11-20 05:18(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:2026-11-20 04:39最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 8 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 04:38(北京时间)
新论文 · v1arXiv:2611.17639

What LLM Agents See and What Users Say

Yue Zhao, Angela Huyue Zhang, S. Alex Yang, Hua Wei, Xiyang Hu

原文摘要

Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from linguistics: an agent may act only if each claim behind the act (e.g., one reservation fits the name) is seen to hold, answered by the user, or disclosed while the act can be undone. A simple bound shows that when lookups cannot tell one record from two, any agent acts without asking first as often with two records as with one. We then vary whether a search lists, counts, or omits a second match, and whether the user states a claim that a record refutes (e.g., "It is empty"). Under a role-only prompt, a count of a second record leaves most of 36 earlier agents acting on the one they see, whereas listing both stops most. When the user says a record such as a folder is empty, however, a count of its one item stops agents about as often as a listing, and stating the claim mostly cuts acting when it is false. The newest Claude and GPT models always open a counted second record, then never act. When we add a same-name, same-zip customer to a retail benchmark, a lookup returning that customer first led to wrong-account writes in about a quarter of conversations, and one that checks a street the user knows kept completion near the one-customer level. Safe writes therefore need lookups that list or check competing records, and evaluations that vary what tools show.

cs.AI · cs.CL

新论文 · v1arXiv:2611.11024

Phase-Conditioned Reward Shaping for Token-Efficient LLM Reasoning

Zhe Chen, Xiaolin Zhou, Xiyang Hu

原文摘要

Extended reasoning can help language models solve complex problems, but long responses often contain both useful computations and redundant checks. Conventional length penalties encourage shorter responses without distinguishing the functions of intermediate steps. We propose Phase-Conditioned Reward Shaping (PCRS), a framework that combines phase identification with training-time reward allocation. We investigate two classification routes: PCRS-H with a hidden-state classifier and PCRS-T with a frozen text classifier. Our main text classifier implementation assigns overlapping reasoning, execution, and revision labels to native chunks, then uses these labels and exact repetition to adjust existing token penalties. We compare the completed configurations on six mathematical and scientific reasoning benchmarks and examine four reward-weight settings with the text classifier. Compared with a baseline using token-level length penalties, the default text classifier configuration reduces mean response length by 3.13%; sampled Pass@1 is approximately 62.07% for both methods, while oracle Pass@16 rises from 86.08% to 87.67%. These results show how phase-informed penalty allocation can reduce output volume and improve multi-attempt coverage without inference-time classification.

cs.LG · cs.AI

版本更新 · v4arXiv:2604.17299

Cat-DPO: Category-Adaptive Safety Alignment

Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Henry Peng Zou, Kaize Ding, Xiyang Hu, Yan Liu 等 9 位作者

原文摘要

Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most preference-based safety alignment methods collapse safety into a single scalar that is applied uniformly to every preference pair. The result is a model that appears safe on average but remains relatively unsafe in a minority of harm categories. We cast safety alignment as a per-category constrained optimization problem and derive Cat-DPO, a direct-preference-optimization algorithm with a separate adaptive safety margin for each harm category. The margin tightens when the model still produces unsafe responses in a category and relaxes once the model catches up, so the training signal tracks each category's current difficulty rather than averaging across a single global rate. Across two LLM backbones and six preference-learning baselines, Cat-DPO improves aggregate helpfulness and harmlessness and compresses per-category safety variance and the best-to-worst gap, offering a drop-in per-category refinement of direct preference safety alignment.

cs.CL · cs.AI

版本更新 · v3arXiv:2605.11928

AgentRobustBench: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

Xiaolin Zhou, Aojie Yuan, Zheng Luo, Zipeng Ling, Xixiao Pan, Yicheng Gao, Haiyue Zhang, Jiate Li 等 15 位作者

原文摘要

Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments violate all these assumptions: user typos propagate into hallucinated tool names, a misconfigured request timeout can stall an agent indefinitely, and duplicate tool names across servers can freeze an SDK. We study these failures as a sim-to-real gap in the tool-use partially observable Markov decision process (POMDP), where deployment noise enters through the observation, action space, reward-relevant metadata, or transition dynamics. We introduce AgentRobustBench, a benchmark with 22 perturbation types organized by these four POMDP components, each grounded in a verified GitHub issue or documented tool-calling failure. Across 21 models from 1.5B to 32B parameters (including the closed-source o4-mini), the robustness profile is sharply uneven: observation perturbations reduce accuracy by less than 5%, while reward-relevant and transition perturbations reduce accuracy by roughly 40% and 30%, respectively; scale alone does not close these gaps. We then propose ToolRL-DR, a domain-randomization reinforcement learning (RL) recipe that trains a tool-use agent on perturbation-augmented trajectories spanning the three statically encodable POMDP components. On a 3B backbone, ToolRL-DR-Full retains roughly three-quarters of clean accuracy and reaches an aggregate perturbed accuracy comparable to open-source 14B function-calling baselines while substantially narrowing the gap to o4-mini. It closes approximately 27% of the Transition gap despite never seeing transition perturbations in training, suggesting that RL on adversarial static tool-use inputs induces a more persistent retry policy that transfers to unseen runtime failures. Code, dataset, checkpoints, and leaderboard are accessible through our GitHub repository.

cs.AI

新论文 · v1arXiv:2611.01620

Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and Monitorability

Sichao Li, Sai Ma, Xiyang Hu, Chudi Zhong, Tongliang Liu

原文摘要

A common assumption in chain-of-thought (CoT) oversight is that a visible reasoning trace makes model behavior easier to monitor. We argue that this assumption can conflate distinct properties along a chain linking a model's internal computation, reasoning artifacts, outputs, and monitor judgments. We identify four properties along this chain: reasoning visibility (whether a trace is accessible), mechanistic faithfulness (whether a trace reflects internal computation), mechanistic localizability (whether a compact causal mechanism can be isolated), and behavioral monitorability (whether a monitor can detect the target behavior). Two complementary case studies across three open-weight reasoning models show why these distinctions matter. In the security vulnerability reasoning study, probes and activation ablations provide evidence of internal representation and causal influence, but a monitor with access to the reference answer does not outperform the majority-class baseline in a held-out test. In authority-hint factual reasoning study, a monitor correctly distinguishes changed from unchanged answers, but seven mechanistic analyses do not isolate a compact causal mechanism. These results show that evidence for one claim does not establish the others. We therefore propose an evidential-chain reporting standard. Each claim carries a licensing statement that specifies its target property, access tier, and artifact, and labels each required link as supported, unsupported, or assumed. These assessments determine whether the conclusion is licensed, conditionally licensed, or not licensed.

cs.AI · cs.CR

版本更新 · v2arXiv:2608.29109

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Yucheng Du, Xiyang Hu

原文摘要

Large language models often answer structurally unanswerable questions, such as computing cot(-540°) or evaluating (1).startswith("1"), instead of abstaining. We ask whether this failure reflects missing recognition or failed routing from recognition to abstention. Across instruction-tuned models from 1.7B to 70B parameters, a single linear direction in the hidden state separates answerable from structurally impossible math and code prompts, showing that models represent impossibility before generation. Yet this recognition direction is nearly orthogonal to the canonical safety-refusal direction that mediates trained harmful-content refusal. An in-domain behavior-defined invalidity-aware direction is closer to recognition, but only partially aligned with it, and remains near-orthogonal to safety refusal. Generation-time steering along the recognition direction changes invalidity-aware behavior bidirectionally and dose-responsively on structural math and code cells, while random directions do not. Base/instruct comparisons further show that the low-cosine geometry is already present at the pretraining endpoint. The confident-on-impossible failure is therefore better explained as a routing failure than as an encoding failure: the model has a usable "no admissible answer" signal, but the safety-refusal pathway is not aligned to use it.

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2039ACL Anthology · ACL 2026

Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models

Zheng Luo, T Pranav Kutralingam, Ogochukwu N. Okoani, Wanpeng Xu Arizona State University, Hua Wei Arizona State University, Xiyang Hu Arizona State University

原文摘要

Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls. While recent work reports strong tool-calling performance under standard English-centric evaluations, the robustness of tool calling under multilingual user interactions remains underexplored. In this work, we introduce MLCL, a diagnostic benchmark, and conduct a systematic evaluation of multilingual tool calling across Chinese, Hindi, and the low-resource language Igbo. Through fine-grained error analysis, we show that many failures occur despite correct intent understanding and tool selection. We identify parameter value language mismatch as a dominant failure mode, where models generate semantically appropriate parameter values in the user’s language, violating language-invariant execution conventions. We further evaluate several inference-time system strategies and find that while these strategies substantially reduce language-induced execution errors, none of them can fully recover English-level performance.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.413ACL Anthology · ACL 2026

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization

Tiancheng Xing National University of Singapore, Jerry Li, Yixuan Du, Xiyang Hu Arizona State University

原文摘要

Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First (RAF), a two-stage token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings while remaining hard to detect. Stage 1 uses Greedy Coordinate Gradient to shortlist candidate tokens at the current position by combining the gradient of the rank-target with a readability score; Stage 2 evaluates those candidates under exact ranking and readability losses using an entropy-based dynamic weighting scheme, and selects a token via temperature-controlled sampling. RAF generates ranking-promoting prompts token-by-token, guided by dual objectives: maximizing ranking effectiveness and preserving linguistic naturalness. Experiments across multiple LLMs show that RAF significantly boosts the rank of target items using naturalistic language, with greater robustness than existing methods in both promoting target items and maintaining naturalness. These findings underscore a critical security implication: LLM-based reranking is inherently susceptible to adversarial manipulation, raising new challenges for the trustworthiness and robustness of modern retrieval systems. Our code is available at: https://github.com/glad-lab/RAF.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表