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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 05:44 — 2026-11-18 05:44(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 14 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2606.22673

Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents

Weidi Luo, Qiming Zhang, Yihao Quan, Mingyu Jin, Jie Cai, Chaowei Xiao, Jingcheng Niu, Zhen Xiang

原文摘要

Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrails, which have a limited ability to perform fine-grained behavioral control during execution. Meanwhile, recent mechanistic interpretability methods for LLM safety are mostly confined to single-turn or jailbreak-style QA settings, limiting their ability to capture the evolving risk dynamics of multi-turn agent execution. In this paper, we investigate the safety of multi-turn CLI agents from an internal perspective. We propose Agent MechSuits (Mechanistic Subspace Intervention and Steering), a white-box defense framework that performs runtime safety detection and representation-level mitigation for CLI agents. Unlike conventional agent guardrails, Agent MechSuits detects harmful execution states from step-level hidden representations and mitigates unsafe behavior by intervening in a 10-dimensional subspace within a single layer. To support this research, we introduce the Mechanistic Agent Safety (MAS) benchmark, comprising comprehensively annotated multi-turn execution trajectories across 194 tasks using LLaMA-3.1-8B, Qwen-2.5-7B, and Gemma-2-9B. Extensive experiments show that Agent MechSuits achieves strong safety detection performance, provides preliminary evidence for lookahead risk anticipation, and substantially reduces harmful actions of the CLI agent, establishing a foundation for applying mechanistic interpretability to dynamic LLM agent safety.

cs.AI · cs.SE

版本更新 · v2arXiv:2603.00397

TENG-BC: Time-Evolving Natural Gradient for High-Accuracy Neural PDE Solvers with General Boundary Conditions

Hongjie Jiang, Di Luo

原文摘要

Accurately solving time-dependent partial differential equations (PDEs) with neural networks remains challenging due to long-time error accumulation and the difficulty of enforcing general boundary conditions. We introduce TENG-BC, a high-precision neural PDE solver based on the Time-Evolving Natural Gradient, designed to perform under generic boundary constraints. At each time step, TENG-BC performs a boundary-aware optimization that jointly enforces interior dynamics and boundary conditions, accommodating Dirichlet, Neumann, Robin, and mixed types within a unified framework. This formulation admits a natural-gradient interpretation, enabling stable time evolution without delicate penalty tuning. Across benchmarks over diffusion, transport, and nonlinear PDEs with various boundary conditions, TENG-BC achieves solver-level accuracy under comparable sampling budgets, outperforming conventional solvers and physics-informed neural network (PINN) baselines.

cs.LG

版本更新 · v2arXiv:2610.37166

LiveSearch:将问题作为可执行验证器代码,用于专业来源金融搜索智能体的实时基准

LiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents

Sinuo Wang, Wentao Zhao, Jiacheng Lu, Rui Sun, Beidi Luan, Qiming Shi, Jing Li, Daxin Jiang 等 9 位作者

AI 速读 基于摘要

LiveSearch 把金融问题存成可执行的验证器程序,在评测时调用专业金融数据服务动态生成金标准答案,从而构建一个答案会随市场变化而更新的实时基准。

cs.AI

查看原文摘要

In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capability of a financial agent. Yet most financial benchmarks overlook timeliness. They fix each answer at annotation time, so the gold goes stale as markets move and, once leaked into training data, rewards recall rather than search and analysis. We introduce LiveSearch, a live benchmark that stores each question as executable verifier code: a typed program of calls to a professional financial data service, followed by a declarative extractor. The question is frozen, while its gold answer is determined by executing the program against professional financial data at evaluation time, and a daily job re-executes it with no human or language model in the loop. A memorized answer is thus likely outdated, and a model must reach the current one through tools and analysis. Construction is equally automatic: a language model only verbalizes programs enumerated from real tool responses and never chooses an answer. Under general web search, six contemporary tool-calling models reach 70.9% to 76.7% answer accuracy. Over three consecutive days, 70% of served questions change their gold value, and even under tolerance-aware matching, a literally reused earlier snapshot fails on a majority of questions within a single day. Per-question tracking uncovers dynamic shifts in correctness masked by aggregate accuracy.

新论文 · v1arXiv:2611.12170

Optimal Proximity Black Hole Search with Programmable Matter

Giuseppe Antonio Di Luna, Alfredo Navarra, Francesco Piselli

原文摘要

The concept of programmable matter (PM) envisions objects composed of tiny, mobile particles capable of self-arrangement, which allows them to change shape, color, and move. We initiate the study of the Black Hole Search problem within the context of PM. The problem involves a dangerous and unnoticeable location, the black hole, that, without a trace, destroys any particle visiting it. In our setting, particles move inside a convex area embedded in a triangular grid, where one vertex is a black hole. The objective is for the particles to identify a restricted set of vertices containing the black hole while ensuring that at least one particle survives. We present an algorithm utilizing three particles capable of assuming just two colors to identify the dangerous region where the black hole resides. Furthermore, we demonstrate that this algorithm is Pareto optimal in terms of number of particles and number of colors required, and asymptotically optimal in terms of number of epochs, where an epoch refers to the minimal time window within which each particle completed an activation cycle at least once.

cs.DC

新论文 · v1arXiv:2611.11497

TID System for Speech-COSER Challenge 2026: ASR Track

Fernando López, Jordi Luque

原文摘要

We describe the system submitted by Telefónica Innovación Digital to the Speech-COSER Challenge 2026, which features spontaneous speech from elderly speakers recorded in rural Spain. For ASR, we perform CTC-based pseudo-forced alignment scores audio-text match quality to guide a two-stage LoRA curriculum, followed by post-hoc magnitude pruning of the LoRA matrices to enhance generalization. An ensemble of seven systems combined via ROVER achieves 36.25\% unnormalized and 22.17\% normalized WER.

cs.CL · cs.AI

新论文 · v1arXiv:2611.11299

EASE-KV: Diagnosing the Gap Between Memory Availability and Effective Use

Di Lu, Zechen Li, Xuanyu Yue, Jiabo Fan, Hao Xue, Flora D. Salim

原文摘要

Reusable key-value (KV) memory avoids repeatedly prefilling retrieved text, but stored and injected memories do not necessarily become usable evidence. We present EASE-KV, a controlled framework for understanding this gap under fixed candidates and a frozen language model. EASE-KV separates three interfaces: whether required relations are preserved during encoding, whether preserved memories receive appropriate influence during allocation, and whether outcome supervision can identify useful allocations. Matched experiments show that causal encoding improves compositional accuracy by 25.0 percentage points over block-diagonal encoding, while the tested inference-time bridging methods fail to recover the lost contextual information. With unchanged stored states, diagnostic evidence-guided allocation improves LongMemEval accuracy from 31.2% to 38.4%, demonstrating that memory influence can be controlled without re-encoding. However, controllability does not guarantee learnability: binary correctness provides informative reward contrast for 53.0% of sampled query groups, compared with 73.6% under the evaluated shaped-reward setting. These findings show that effective KV memory requires more than retrieval and injection: the required relations must be encoded, preserved memories must receive appropriate influence, and supervision must distinguish better allocations from worse ones.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.03953

P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors

Sinuo Wang, Jiacheng Lu, Zeyu Zhang, Maojia Song, Rui Sun, Beidi Luan, Yutong Xie, Jing Li 等 11 位作者

原文摘要

Multi-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear parameter combinations. We view the linear combination of student and expert parameters as a single differentiable model and propose P$^2$-MOPD, which jointly optimizes the mixing coefficients and the student weights under the same on-policy distillation objective. Unlike task arithmetic, which stays within the span of the frozen student and expert parameters for any choice of merging coefficients, P$^2$-MOPD keeps the student trainable, so the experts act as parameter priors without confining it to this span. Across four domains at 1.7B and 4B scales, P$^2$-MOPD achieves faster and more balanced recovery than MOPD from the same initialization, surpassing its final average recovery in half the training steps. At the end of training, our 1.7B model reaches 94.7% average recovery, versus 80.9% for MOPD.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.36980

AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations

Qiming Shi, Yikun Li, Beidi Luan, Rui Sun, Sinuo Wang, Delin Wang, Yan Ma, Jing Li 等 10 位作者

原文摘要

Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2O) commerce, decisions are issued through Web-based platforms but realized through costly physical execution. Evaluating such agents requires going beyond individual transactions to ask whether decisions made online turn into sustained economic returns. We introduce AutoVend, a benchmark in which one LLM agent manages 20 vending machines across five site types through a Web-based operating interface for 180 simulated days. Its data-grounded simulator combines a shared warehouse, procurement lead times, paid replenishment, inventory expiration, and recurring operating costs. We evaluate five LLM agents against a rule-based inventory-control baseline and diagnose their site coordination, execution, and performance over time. Four of five evaluated LLM agents fall short of this baseline, and returns per dollar of inference cost rank models differently from returns alone. Operational analyses show that gains in individual metrics do not consistently yield stronger economic growth, as inventory and execution costs erode these gains. Trajectory analysis further reveals difficulties in grounding feasible actions, managing inventory commitments, and converting feedback into effective policy revisions.

cs.AI · cs.CL

新论文 · v1arXiv:2611.02480

Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory

Di Lu, Zechen Li, Hao Xue

原文摘要

Long-term conversational memory faces a timing mismatch: write-time summaries and graphs organize history before a future query is known, while independent retrieval can allocate a limited evidence budget to redundant or fragmented turns. We introduce Chain on Demand (CoD), a query-time evidence organization framework over an unchanged turn-level memory. Given a broad candidate pool, CoD constructs a temporary evidence chain by allocating a fixed anchor budget according to query relevance, lexical diversity relative to selected anchors, and newly covered query terms, followed by deterministic restoration of each selected anchor's same-session neighborhood. The resulting chain is used only for the current query, while the underlying conversational memory remains unchanged. In a paired comparison over all 1,986 LoCoMo questions, CoD achieves 82.2% accuracy on 1,540 non-adversarial questions and 76.3% on all 1,986 questions. On LongMemEval-S, one fixed configuration that indexes both user and assistant turns obtains 86.6% across all 500 questions. These results show that long-term memory can preserve the original conversation while deferring evidence organization until the information need is known.

cs.CL · cs.AI

新论文 · v1arXiv:2611.01831

MATE: Multi-Agent Traffic Engineering for Topology-Aware Distributed SRv6 Scheduling under Bursty Traffic

Yuang Chen, Shuyi Liu, Chengdi Lu, Fengqian Guo, Hancheng Lu, Chang Wen Chen

原文摘要

As network traffic becomes increasingly dynamic and bursty, conventional centralized traffic engineering (TE) suffers from long control-loop delays caused by network-state aggregation, centralized computation, and policy distribution. In this paper, we propose MATE, a multi-agent TE method for proactive distributed scheduling in hybrid networks with partial deployment of Segment Routing over IPv6 (SRv6). MATE uses historical traffic stability to characterize the burst risk of each traffic demand and path sensitivity to quantify the ability of candidate paths to accommodate additional traffic, thereby enabling differentiated proactive scheduling tailored to heterogeneous traffic characteristics. MATE adopts an offline-centralized training and online-distributed execution architecture. During training, a shared global critic evaluates joint actions under a reward combining maximum link utilization (MLU) with variability-weighted path sensitivity, while counterfactual difference rewards provide agent-specific credit for actor learning. During online execution, edge agents generate traffic-splitting policies from local observations and apply them through SRv6, avoiding centralized optimization in each scheduling interval. Experiments on the China Environment for Network Innovations (CENI) testbed and simulations on the Sanet topology show that MATE outperforms a multi-agent reinforcement learning (MARL) ablation baseline without agent-specific credit assignment, COPE, and TEAL in most evaluated scenarios and approaches centralized FIGRET on measured traffic traces. On CENI-Abilene, MATE achieves MLU within 10% of the linear-programming optimum in up to 90.1% of test instances. MATE also achieves lower median normalized MLU than FIGRET in most tested failure scenarios, with mean neural-inference times of 2.05--3.14~ms.

cs.NI

新论文 · v1arXiv:2611.01761

Computation in Anonymous Directed Dynamic Networks: Exact Worst-Case Termination Time and Network-Wise Intractability

Giuseppe A. Di Luna, Giovanni Viglietta

原文摘要

We determine the exact round complexity of Counting in anonymous directed dynamic networks. Agents have no identifiers, but $\ell\geq1$ of them are designated as leaders. Every agent knows $\ell$ and its own leader status, while the population size $n$ is unknown and has to be determined by the agents. Communication proceeds in synchronous rounds; the directed communication graph may change arbitrarily and unpredictably from one round to the next, but is assumed to remain strongly connected. We solve Counting with a distributed algorithm that makes every agent output $n$ and halt after a number of rounds equal to $\begin{cases} n&\text{if }n=\ell\\ 2n-1&\text{if }n>\ell\text{ and }\ell=1\\ 2n-2&\text{if }n>\ell\text{ and }\ell\geq2. \end{cases}$ The algorithm works even for networks with loops and parallel arcs and even when agents learn their outdegree only after sending. We prove that this bound is worst-case tight over directed multigraphs for every $n$ and $\ell$ with $1\leq\ell\leq n$. Moreover, the local computation is polynomial (provided that each communication multigraph has at most $2^{\operatorname{poly}(n)}$ arcs): in every round, each agent solves at most one linear system with up to $n$ variables. By standard techniques, solving Counting also enables the evaluation of any computable function of the multiset of agents' input values within $2n-1$ communication rounds. The bound above optimizes the worst case over all networks. For an individual network, we show that even deciding whether an agent already has enough local information to determine $n$ is $\mathsf{coNP}$-complete (provided that the numbers of parallel arcs are encoded in binary). Thus, worst-case-optimal Counting admits polynomial local computation, whereas exact network-wise optimization is intractable under standard complexity assumptions.

cs.DC

新论文 · v1arXiv:2610.36878

RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents

Delin Wang, Sinuo Wang, Rui Sun, Beidi Luan, Qiming Shi, Jing Li, Daxin Jiang, Zuo Bai

原文摘要

Deep research agents conduct multi-step Web searches and synthesise retrieved information into analytical reports. Evaluating these outputs requires checking which analyses they deliver, beyond the presence of relevant facts. Query-specific binary rubrics make individual requirements explicit, but task-level checklists may leave the overall analytical structure underexamined. We introduce RubricAtlas, which derives type-level analytical requirements from expert reports on different objects within the same research type and organises detailed checks around recurring analytical questions. The requirements give related tasks a shared standard for what to analyse, without prescribing their answers. Our framework links binary checkpoints to report passages and evaluates completeness separately from argument validity. Built from 3,079 Chinese financial research reports, RubricAtlas covers 99 research types. Reference-report selection experiments show that individual reports cover only about half of their type's analytical questions, and that selecting requirements from different reports changes evaluation scores and agent rankings. Across ten agents, two judge pipelines achieve checkpoint agreement of $κ$ = 0.71 and agent-ranking agreement of Kendall $τ$ = 0.87. Controlled deletions reduce scores on the affected analyses, while padding produces no detectable increase. These findings support type-level rubrics for comparing the analytical completeness of Web deep research outputs, with individual decisions traceable to report evidence.

cs.AI · cs.CL

版本更新 · v4arXiv:2610.21561

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents

Sergio Burdisso, Esaú Villatoro-Tello, Dairazalia Sánchez-Cortés, Yanis Labrak, Jordi Luque, Milos Cernak, Petr Motlicek

原文摘要

Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has received extensive attention, a different failure mode has been overlooked: procedural hallucination, in which an agent produces individually fluent and factually plausible utterances while deviating from the intended conversational process. We introduce DialFork, the first benchmark to measure this failure mode on raw dialogue text. DialFork is built by forking conformant dialogues at controlled turn positions and injecting one of four hallucination types, yielding 36,278 dialogues across 24 tasks in 12 domains; 30 human annotators validate the construction. We define three evaluation tasks that characterize procedural deviation at three granularities: how far a set of dialogues deviates from conformant ones (monitoring deployed agents), how far a single dialogue does (procedural retrieval), and at which turn a dialogue first goes off-track (real-time guardrails). For the first two, we propose dialog-flow-aware metrics, FlowKL and FlowScore, that compare dialogues by how they unfold rather than their content. At the dialogue level, FlowScore significantly outperforms all baselines across seven encoders, showing that semantic similarity is no substitute for procedural similarity. We release DialFork under open licenses at https://github.com/idiap/dialfork, hoping the community will measure conversational process alongside content.

cs.CL · cs.AI · cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-short.19ACL Anthology · ACL 2026

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

Zhenwen Liang Tencent AI Lab, Yujun Zhou University of Notre Dame, Sidi Lu ByteDance Seed, Xiangliang Zhang University of Notre Dame, Haitao Mi Tencent AI Lab, Dong Yu CapitalOne

原文摘要

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure cases causes the advantage signal in group-relative algorithms (e.g., GRPO) to vanish, driving policies into mode collapse. To address this, we propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration. Unlike standard sampling that follows model biases, CUTS flattens the local optimization landscape by sampling uniformly from constrained high-confidence candidates. We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance. Experiments on Qwen3 models demonstrate that our approach prevents policy degeneration and significantly boosts out-of-domain generalization. Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO, validating that maintaining diversity within the semantic manifold is critical for rigorous reasoning.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表