arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

共收录 93793 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 工具调用 5118 篇

1811.09382 2018-11-26 cs.RO 67%

A Blended Human-Robot Shared Control Framework to Handle Drift and Latency

Anas Abou Allaban, Velin Dimitrov, Taşkın Padır

专题命中 工具调用 :agent(abstract);autonomous agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
1806.06933 2018-06-20 cs.GT cs.DS 67%

Delegated Search Approximates Efficient Search

Jon Kleinberg, Robert Kleinberg

专题命中 工具调用 :agent(abstract);workflow(abstract)

Comments An extended abstract of this work appears in the Proceedings of the 19th ACM Conference on Economics and Computation (EC), 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
1710.05133 2017-11-30 math.OC 67%

Tracking Moving Agents via Inexact Online Gradient Descent Algorithm

Amrit Singh Bedi, Paban Sarma, Ketan Rajawat

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
1702.05573 2017-02-21 cs.CV 67%

Collaborative Deep Reinforcement Learning for Joint Object Search

Xiangyu Kong, Bo Xin, Yizhou Wang, Gang Hua

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
1511.05869 2016-10-23 cs.ET 67%

Mechanisms Inducing Parallel Computation in a Model of Physarum polycephalum Transport Networks

Jeff Jones

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

Journal ref Transport Networks, Parallel Processing Letters, (25), 1, 1540004 (2015)

详情

展开后加载摘要…

URL PDF HTML 收藏
1009.5566 2015-05-20 astro-ph.SR 67%

A high resolution, multi-epoch spectral atlas of peculiar stars including RAVE, GAIA and HERMES wavelength ranges

L. Tomasella, U. Munari, T. Zwitter

专题命中 工具调用 :tool use(abstract);planning(abstract)

Comments AJ in press (issue 140:6 December 2010)

详情

展开后加载摘要…

URL PDF HTML 收藏
0911.4729 2015-03-13 cs.DM cs.DC physics.comp-ph physics.soc-ph 67%

Hearing the clusters in a graph: A distributed algorithm

Tuhin Sahai, Alberto Speranzon, Andrzej Banaszuk

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
1401.5390 2014-01-22 cs.CL cs.AI cs.LG 67%

Learning to Win by Reading Manuals in a Monte-Carlo Framework

S. R. K. Branavan, David Silver, Regina Barzilay

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.CL、cs.LG

Journal ref Journal Of Artificial Intelligence Research, Volume 43, pages 661-704, 2012

详情

展开后加载摘要…

URL PDF HTML 收藏
1312.4601 2013-12-18 cs.RO 67%

Strategic Control of Proximity Relationships in Heterogeneous Search and Rescue Teams

Eduardo Feo Flushing, Luca M. Gambardella, Gianni A. Di Caro

专题命中 工具调用 :agent(abstract);planning(abstract)

Comments In Proceedings of the 3rd IROS Workshop on Robots and Sensors integration in future rescue INformation system (ROSIN), Tokyo, Japan, November 7, 2013

详情

展开后加载摘要…

URL PDF HTML 收藏
1207.4163 2012-07-19 cs.GT 67%

Reputation Systems: An Axiomatic Approach

Moshe Tennenholtz

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

Comments Appears in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI2004)

详情

展开后加载摘要…

URL PDF HTML 收藏
1207.3682 2012-07-17 cs.GT 67%

Matching Games with Additive Externalities

Simina Brânzei, Tomasz P. Michalak, Talal Rahwan, Kate Larson, Nicholas R. Jennings

专题命中 工具调用 :agent(abstract);tool use(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
cs/0703072 2009-12-01 cs.OH 67%

Domain Directed Dialogs for Decision Processes

Paul Fodor

专题命中 工具调用 :planning(abstract);workflow(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
astro-ph/0701669 2009-12-01 astro-ph 67%

Simulation tool of a Supernova search with VST

R. Calvi, E. Cappellaro, M. T. Botticella, M. Riello

专题命中 工具调用 :tool use(abstract);planning(abstract)

Comments Published in the Proceedings of the "I Workshop of Astronomy and Astrophysics for Students", Eds. N.R. Napolitano & M. Paolillo, Naples, 19-20 April 2006 (astro-ph/0701577)

详情

展开后加载摘要…

URL PDF HTML 收藏
cs/0509017 2009-12-01 cs.MA cs.CE 67%

Traders imprint themselves by adaptively updating their own avatar

Gilles Daniel, Lev Muchnik, Sorin Solomon

专题命中 工具调用 :agent(abstract);multi-agent(abstract)

Comments 12 pages, 4 figures, draft of a paper submitted to Artificial Economics 2005, September 15-16, Lille, France

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18764 2026-03-06 cs.AI cs.CL 66%

The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol

模式引导对话系统与模型上下文协议的收敛

Andreas Schlapbach

机构 * SBB-IT

专题命中 工具调用 :agent(abstract,comments);分类 cs.AI、cs.CL

AI总结 本文通过分析模式引导对话系统与模型上下文协议的收敛,提出五条模式设计原则,揭示了SGD与MCP的内在联系及软件3.0中的关键监督机制。

Comments 18 sections, 4 figures, 7 tables, 40 references. Original research presenting: (1) formal framework mapping Schema-Guided Dialogue principles to Model Context Protocol concepts, (2) five foundational design principles for LLM-native schema authoring, (3) architectural patterns for secure, scalable agent orchestration. Research supported by SBB (Swiss Federal Railways)

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.15041 2025-11-27 cs.AI cs.LG cs.SY eess.SY 66%

Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search

地球观测卫星调度与图神经网络及蒙特卡洛树搜索

Antoine Jacquet, Guillaume Infantes, Emmanuel Benazera, Vincent Baudoui, Jonathan Guerra, Stéphanie Roussel

专题命中 工具调用 :planning(abstract,comments);分类 cs.AI、cs.LG

AI总结 本文提出利用图神经网络和深度强化学习结合蒙特卡洛树搜索,解决地球观测卫星调度问题,以提高调度效率和效益。

Comments Accepted at International Workshop on Planning & Scheduling for Space (IWPSS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.00277 2025-04-02 cs.AI cs.DC cs.LG cs.NI math.OC 66%

Rack Position Optimization in Large-Scale Heterogeneous Data Centers

Chang-Lin Chen, Jiayu Chen, Tian Lan, Zhaoxia Zhao, Hongbo Dong, Vaneet Aggarwal

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.LG;planning(comments)

Comments Extended version of paper accepted at The International Conference on Automated Planning and Scheduling (ICAPS) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.04935 2024-06-10 cs.AI cs.LG 66%

SLOPE: Search with Learned Optimal Pruning-based Expansion

Davor Bokan, Zlatan Ajanovic, Bakir Lacevic

专题命中 工具调用 :planning(abstract,comments);分类 cs.AI、cs.LG

Comments presented at the ICAPS 2024 workshop on Bridging the Planning and Reinforcement Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2108.00978 2021-08-03 cs.AI cs.LG cs.RO 66%

Constrained Shortest Path Search with Graph Convolutional Neural Networks

Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

专题命中 工具调用 :planning(abstract,journal_ref);分类 cs.AI、cs.LG

Journal ref AAAI - ICML / IJCAI / AAMAS 2018 Workshop on Planning and Learning (PAL-18). Stockholm, Sweden 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.06460 2020-10-14 cs.AI cs.LG physics.flu-dyn physics.soc-ph 66%

Deep Reinforcement Learning for Real-Time Optimization of Pumps in Water Distribution Systems

Gergely Hajgató, György Paál, Bálint Gyires-Tóth

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.LG;planning(journal_ref)

Journal ref Journal of Water Resources Planning and Management, Volume 146, Issue 11 (November 2020)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06982 2025-12-12 cs.LG cs.SY eess.SY 65%

LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding

基于大语言模型的多源强化学习状态编码复合神经架构搜索

Yu Yu, Qian Xie, Nairen Cao, Li Jin

机构 * Shanghai Jiao Tong University(上海交通大学) Cornell University(康奈尔大学) New York University(纽约大学)

专题命中 工具调用 :agent(abstract,comments);分类 cs.LG;planning(comments)

AI总结 本文提出基于大语言模型的复合神经架构搜索方法,用于多源强化学习状态编码,通过高效搜索发现更高性能的编码器架构。

Comments NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

详情

展开后加载摘要…

URL PDF HTML 收藏
1007.0776 2012-04-18 cs.AI cs.CC cs.GT 65%

Is Computational Complexity a Barrier to Manipulation?

Toby Walsh

专题命中 工具调用 :tool use(abstract);分类 cs.AI;agent(comments);multi-agent(comments)

Comments To appear in Proceedings of 11th International Workshop on Computational Logic in Multi-Agent Systems (CLIMA XI 2010)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06087 2026-08-27 cs.CL cs.AI 版本更新 62%

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

LatentSkill: 从上下文文本技能到LLM智能体的权重内隐技能

Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo, Rong Shan, Zhihui Fu, Jun Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin

机构 * Shanghai Jiao Tong University(上海交通大学) Sun Yat-Sen University(中山大学) Shanghai Innovation Institute(上海创新研究院) OPPO Research Institute(OPPO研究院)

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.CL

AI总结 提出LatentSkill框架,通过预训练超网络将文本技能转换为即插即用的LoRA适配器,将技能知识存储在权重空间而非上下文空间,从而减少预填充令牌并提升性能。

Comments 10 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.24804 2026-08-26 cs.AI cs.SE 新提交 62%

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

StarHarness:针对企业环境的分层搜索进化 harness(工具适配层)

Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav, Sai Rajeswar, Patrice Bechard, Sridhar Nemala, Sagar Davasam

机构 * ServiceNow(ServiceNow公司) Mila(米拉研究所) Université de Montréal(蒙特利尔大学)

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.SE

AI总结 StarHarness是一种固定模型权重的harness进化框架,经分层搜索优化后,在ITBench等3个企业任务基准上性能提升20-35个百分点,且可跨GPT、Qwen模型迁移,缓解模型-环境不匹配问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.24571 2026-08-26 cs.AI cs.SE 新提交 62%

Joint Optimization of Tool Creation and Use for Large Language Model Agents

大型语言模型智能体的工具创建与使用联合优化

Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Shao-Hua Sun, Hung-yi Lee

机构 * Appier AI Research(沛星人工智能研究院) National Taiwan University(台湾大学)

专题命中 工具调用 :tool use(abstract);分类 cs.AI、cs.SE

AI总结 提出SMITH框架联合训练工具创建与使用,4B Qwen3经训练在多任务上取得最优表现,其编写的工具还提升了其他模型的推理性能

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.23651 2026-08-26 cs.SE cs.AI 新提交 62%

Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail

适得其反的反馈:为什么小型语言模型智能体重复它们刚刚看到的失败调用

Esmail Gumaan

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.SE

AI总结 该研究发现小型语言模型智能体的失败工具调用反馈会适得其反,调用表面形式是主要原因,替换失败描述或使其不可达可减少重复,明确指令或删除失败尝试无效。

Comments 25 pages, 6 figures, 13 tables. Code, data, probe items and rollout logs: https://github.com/Esmail-ibraheem/feedback-that-backfires

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.04565 2026-08-25 cs.CR cs.AI cs.CL 版本更新 62%

Breadcrumbing Search Agents

面包屑式搜索智能体

Xuebin Li, Hanqing Zhao, Siyuan Liang, Kejiang Chen, Weiming Zhang, Dacheng Tao, Nenghai Yu

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.CL

AI总结 该研究针对LLM搜索智能体的安全问题,提出ACH和TGSE策略,通过操纵搜索结果形成连贯证据链,大幅提升攻击成功率。

Comments 39 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.01548 2026-08-21 cs.AI cs.LG 版本更新 62%

LLM Capability Limits: Static Emergence and Dynamic Boundary Control

涌现不变性:从符号化思维到结构控制

Yi Liu

专题命中 工具调用 :tool use(abstract);分类 cs.AI、cs.LG

AI总结 该研究形式化了语言为核心的智能的限制,提出动态边界控制框架,通过DeepSeek V4-Flash实验验证其可提升大语言模型的推理性能,组织了大语言模型的涌现限制。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17381 2026-08-19 q-bio.QM cs.AI cs.LG q-bio.BM 新提交 62%

Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design

利用生成式幻觉和生物物理引导建模实现统一的生物分子序列-结构协同设计

Xuefeng Liu, Mingxuan Cao, Xiao Luo, Songhao Jiang, Tobin Sosnick, Jinbo Xu, Louis Maher, Rick Stevens

专题命中 工具调用 :planning(abstract);分类 cs.AI、cs.LG

AI总结 研究针对DNA/RNA等生物分子设计难题,提出MCTH框架,通过蒙特卡洛树搜索实现序列-结构协同设计,在多模态设计任务中性能优于基线,且可跨模态泛化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07531 2026-08-19 cs.CL cs.AI 版本更新 62%

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

Search-G1:基于表征内在奖励的接地搜索智能体

Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang, Ranjie Duan, Qiaolin Xia, Hao Wang, Yu Lu, Haibo Shi, Xingjun Ma

专题命中 工具调用 :agent(abstract);分类 cs.AI、cs.CL

AI总结 该研究提出Search-G1框架,通过两个经干预校准的读数构成的表征内在奖励,改善了搜索增强语言智能体的接地性与搜索成本的权衡,在多基准和模型规模上验证了其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏