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 93149 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 规划决策 35504 篇

2602.21255 2026-07-14 cs.GT cs.AI math.OC 版本更新 91%

A General Equilibrium Theory of Orchestrated AI Agent Systems

一个 orchestrated AI agent 系统的一般均衡理论

Jean-Philippe Garnier

专题命中 规划决策 :agent(title,title_cn);AI agent(title,title_cn);分类 cs.AI

AI总结 本文提出了一种基于一般均衡理论的AI代理系统模型,通过集中编排实现系统福利最大化,并证明了均衡存在性和收敛性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16966 2026-07-13 cs.CR cs.AI 91%

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning

视觉 inception:通过多模态记忆污染在代理推荐系统中妥协长期规划

Jiachen Qian

机构 * City University of Hong Kong(香港城市大学)

专题命中 规划决策 :agentic(title,abstract);planning(title,abstract);agent(abstract);AI agent(abstract)

AI总结 本文提出视觉 inception 攻击,通过污染用户上传的图片在代理推荐系统中影响长期规划,提出 CognitiveGuard 防御框架以降低攻击风险。

Comments 17 pages, 6 figures, 16 tables

Journal ref Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 20846-20862, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.28692 2026-06-30 cs.AI 91%

An AI agent for treatment reasoning over a biomedical tool universe

一个在生物医学工具宇宙中进行治疗推理的AI智能体

Shanghua Gao, Ayush Noori, Richard Zhu, Curtis Ginder, Zhenglun Kong, Xiaorui Su, Justin Kauffman, Benjamin S. Glicksberg, Joshua Lampert, Ankit Sakhuja, Ashwin Sawant, ATHENA-R1 Evaluation Consortium, David A. Clifton, Noa Dagan, Ran Balicer, Marinka Zitnik

机构 * Department of Biomedical Informatics, Harvard Medical School(哈佛医学院生物医学信息学系) Department of Engineering Science, University of Oxford(牛津大学工程科学系) The Ivan and Francesca Berkowitz Family Living Laboratory Collaboration at Harvard Medical School and Clalit Research Institute(哈佛医学院伊万和弗朗西斯卡·伯科维茨家族生活实验室合作与克莱利研究所) Cardiovascular Division, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School(哈佛医学院心脏病学部,布里格姆和妇女医院) The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院人工智能与人类健康系) The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai and Mount Sinai Health System(西奈山伊坎医学院和西奈山医疗系统数字健康研究所) Mindich Child Health and Development Institute and the Departments of Pediatrics and Genetics & Genomic Sciences, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院Mindich儿童健康与发展研究所及儿科学和遗传学与基因组科学系) Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院Fuster心脏医院) Mount Sinai AI Assurance Lab, Mount Sinai Health System(西奈山医疗系统AI保证实验室) Institute for Critical Care Medicine, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院重症监护医学研究所) Department of Medicine, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院医学系) ATHENA-R1 Evaluation Group(ATHENA-R1评估组)

专题命中 规划决策 :agent(title,abstract);AI agent(title,abstract);tool use(abstract);tool-use(abstract)

AI总结 提出ATHENA-R1智能体,通过强化学习在212种生物医学工具上训练,实现迭代证据收集的治疗推理,在多个基准上超越现有模型,准确率达94.7%。

Comments Project page: https://athena.openscientist.ai Code: https://github.com/mims-harvard/ATHENA

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05275 2026-06-05 cs.CV cs.AI 91%

Personal AI Agent for Camera Roll VQA

个人AI代理用于相机胶卷VQA

Thao Nguyen, Krishna Kumar Singh, Donghyun Kim, Yong Jae Lee, Yuheng Li

机构 * University of Wisconsin-Madison(威斯康星大学麦迪逊分校) Korea University(韩国大学) Adobe Research(Adobe研究院)

专题命中 规划决策 :agent(title,summary_cn);AI agent(title,abstract);分类 cs.AI

AI总结 本文提出camroll数据集和camroll-agent代理,通过层次化记忆和工具集解决个人相机胶卷中的长程、高度个性化的视觉问答问题。

Comments Project page, code, and demo: https://thaoshibe.github.io/camroll

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.00276 2026-05-04 cs.AI 91%

Agentic AI for Trip Planning Optimization Application

基于代理的AI用于旅行计划优化应用

Tiejin Chen, Ahmadreza Moradipari, Kyungtae Han, Hua Wei, Nejib Ammar

机构 * Toyota Motor North America R&D, InfoTech Labs(丰田美国北美研发部门信息科技实验室) Arizona State University(亚利桑那州立大学)

专题命中 规划决策 :planning(title,abstract);agentic(title,abstract);agent(abstract);workflow(abstract)

AI总结 本文提出基于代理的AI框架,通过协调代理优化旅行计划,提供精确解决方案,实验显示其在TOP基准测试中准确率高达77.4%。

Comments Accepted to IV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11062 2026-02-02 cs.LG cs.MA 91%

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

Stronger-MAS: 多智能体强化学习用于协作大语言模型

Yujie Zhao, Lanxiang Hu, Yang Wang, Minmin Hou, Hao Zhang, Ke Ding, Jishen Zhao

机构 * University of California, San Diego(加州大学圣地亚哥分校) Intel Corporation(英特尔公司)

专题命中 规划决策 :agent(title,abstract);multi-agent(title,abstract);planning(abstract);workflow(abstract)

AI总结 Stronger-MAS提出了一种针对多智能体强化学习的AT-GRPO算法,通过改进的分组策略和训练系统,在多个任务中显著提升了大语言模型的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01743 2026-01-06 cs.AI 91%

AI Agent Systems: Architectures, Applications, and Evaluation

AI代理系统:架构、应用与评估

Bin Xu

机构 * School of Electrical, Computer and Energy Engineering, Arizona State University(电气、计算机与能源工程学院,亚利桑那州立大学)

专题命中 规划决策 :agent(title,abstract);AI agent(title,abstract);tool use(abstract);planning(abstract)

AI总结 本文综述了AI代理系统在架构、应用与评估方面的最新进展,探讨了代理组件、协调模式及部署设置,并分析了设计权衡与评估挑战。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01438 2025-06-17 cs.AI 91%

Distinguishing Autonomous AI Agents from Collaborative Agentic Systems: A Comprehensive Framework for Understanding Modern Intelligent Architectures

Prashik Buddhaghosh Bansod

专题命中 规划决策 :AI agent(title,abstract);agentic(title,abstract);agent(abstract);planning(abstract)

Comments There may be overlap with another author's work. I am withdrawing this for me to review further

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13516 2025-05-21 cs.MA cs.AI 91%

HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems

Zhipeng Hou, Junyi Tang, Yipeng Wang

机构 * Nanjing University of Posts and Telecommunications(南京邮电大学) Chongqing University(重庆大学)

专题命中 规划决策 :agent(title,abstract);multi-agent(title,abstract);planning(abstract);workflow(abstract)

Comments The code repository is available at https://github.com/23japhone/HALO

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.03965 2026-06-03 cs.CL cs.AI 91%

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

Agentic Chain-of-Thought Steering:实现高效且可控的LLM推理

Yu Xia, Zhouhang Xie, Xin Xu, Byungkyu Kang, Prarit Lamba, Xiang Gao, Julian McAuley

专题命中 规划决策 :agentic(title,title_cn);agent(abstract);分类 cs.AI、cs.CL

AI总结 提出Agentic Chain-of-Thought Steering (ACTS)方法,通过强化学习训练控制器智能体在推理过程中自适应地选择推理策略和引导短语,实现预算感知的策略控制,从而在保持推理质量的同时显著节省token,并支持准确率-效率的可控权衡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13594 2026-03-17 cs.AI cs.LG 91%

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

EnterpriseOps-Gym:面向企业场景的状态ful代理规划与工具使用的环境与评估

Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar

机构 * ServiceNow Research(ServiceNow研究院)

专题命中 规划决策 :planning(title,abstract);agentic(title,abstract);tool use(title);分类 cs.AI、cs.LG

AI总结 本文提出EnterpriseOps-Gym基准,用于评估企业环境中代理的规划能力。通过164个数据库表和512个功能工具模拟真实工作摩擦,评估14种前沿模型,发现状态-of-the-art模型在战略推理上存在显著不足,且代理常无法拒绝不可行任务。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.21249 2025-10-08 cs.LG cs.AI 91%

Capacity-Aware Planning and Scheduling in Budget-Constrained Multi-Agent MDPs: A Meta-RL Approach

Manav Vora, Ilan Shomorony, Melkior Ornik

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

专题命中 规划决策 :agent(title,abstract);multi-agent(title,abstract);planning(title);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16111 2025-02-25 cs.AI cs.CL 91%

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi

专题命中 规划决策 :agent(title,abstract);planning(title,abstract);multi-agent(title);分类 cs.AI、cs.CL

Comments 30 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.10322 2024-03-15 cs.CV cs.AI cs.CL 91%

CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation

Xiwen Liang, Liang Ma, Shanshan Guo, Jianhua Han, Hang Xu, Shikui Ma, Xiaodan Liang

专题命中 规划决策 :autonomous agent(title,abstract);planning(title,abstract);agent(title);分类 cs.AI、cs.CL

Comments 22 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.00561 2023-05-02 cs.AI cs.FL cs.MA cs.RO cs.SY eess.SY 91%

Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments

Junchao Li, Mingyu Cai, Zhen Kan, Shaoping Xiao

专题命中 规划决策 :autonomous agent(title,abstract);planning(title,abstract);agent(abstract,comments);multi-agent(abstract,comments)

Comments 32 pages, 22 figures, submitted to Autonomous Agents and Multi-Agent Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.29163 2026-05-29 eess.IV 91%

BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery

BCER Agent: 通过编译、工件绑定和有界局部恢复实现可靠的长期MRI工作流执行

Ziyang Long, Xinqi Li, Junzhou Chen, Yifan Gao, Debiao Li, Hsin-Jung Yang

专题命中 规划决策 :agent(title,title_cn);workflow(title,abstract);planning(abstract)

AI总结 提出BCER控制器架构,通过解耦高层规划与执行、有界局部恢复机制,在长链MRI工作流上实现端到端执行一致改进,并保持输出与中间工件的可审计关联。

Comments Pre-review submitted version of a paper accepted to MICCAI 2026. The final authenticated version will be available on SpringerLink

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22138 2026-05-22 cs.AI cs.CL cs.LG cs.RO 91%

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

通过自我调节模拟规划实现高效的代理推理

Mingkai Deng, Jinyu Hou, Lara Sá Neves, Varad Pimpalkhute, Taylor W. Killian, Zhengzhong Liu, Eric P. Xing

机构 * Institute of Foundation Models (IFM)(基础模型研究所) Carnegie Mellon University(卡内基梅隆大学)

专题命中 规划决策 :agentic(title,abstract);planning(title,abstract);agent(abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 本文提出通过分解决策过程为三个系统:模拟推理、自我调节和反应执行,来提升代理推理的效率,并展示了SR$^2$AM模型在不同任务中的表现。

Comments Code and model artifacts are available at https://github.com/sailing-lab/sr2am

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.24039 2026-04-28 cs.LG cs.AI cs.CL 91%

AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents

AgenticCache: 基于缓存的异步规划用于具身AI代理

Hojoon Kim, Yuheng Wu, Thierry Tambe

机构 * Anonymous Institution, Anonymous City, Anonymous Region, Anonymous Country(匿名机构、匿名城市、匿名地区、匿名国家)

专题命中 规划决策 :AI agent(title,abstract);planning(title,abstract);agent(abstract);multi-agent(abstract)

AI总结 本文提出AgenticCache框架,利用缓存重用计划以减少LLM调用,提升任务成功率22%并降低延迟与成本。

Comments Accepted at MLSys 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06366 2025-06-13 q-bio.NC cs.CY cs.MA 91%

AI Agent Behavioral Science

Lin Chen, Yunke Zhang, Jie Feng, Haoye Chai, Honglin Zhang, Bingbing Fan, Yibo Ma, Shiyuan Zhang, Nian Li, Tianhui Liu, Nicholas Sukiennik, Keyu Zhao, Yu Li, Ziyi Liu, Fengli Xu, Yong Li

专题命中 规划决策 :agent(title,abstract);AI agent(title,abstract);planning(abstract);agentic(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.05804 2024-12-03 cs.AI cs.CL cs.SE 91%

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning

Xinzhe Li

专题命中 规划决策 :tool use(title,abstract);planning(title,abstract);agent(abstract);workflow(abstract)

Comments CoLing 2025 Camera Ready (extended to 9 pages)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.13031 2026-08-14 cs.CV cs.AI 新提交 91%

UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations

UniTraffic-Agent:面向2026年AI城市挑战赛第3赛道的统一交通视频推理,含两项域外评估

Peng Li, Qianqian Xu, Shilong Bao, Yangbangyan Jiang, Qingming Huang

机构 * School of Computer Science and Technology, University of Chinese Academy of Sciences (UCAS)(中国科学院大学计算机科学与技术学院) Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)(中国科学院计算技术研究所) Beijing Academy of Artificial Intelligence (BAAI)(北京智源人工智能研究院) School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院)

专题命中 规划决策 :agent(title,title_cn);workflow(abstract);分类 cs.AI

AI总结 UniTraffic-Agent是第10届AI城市挑战赛第3赛道的MR-CAS解决方案,采用观察-推理-行动-验证工作流,在TAR、FETV、PSI-VQA三项任务中取得相应排名,为交通视频推理提供了新方案。

Comments This paper has been accepted to ECCV 2026 AI City Challenge Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07637 2026-08-11 cs.AI cond-mat.mtrl-sci 新提交 91%

Agent-MD: Selective LLM Intervention with Event-Driven Escalation for Stateful GCMC--MD Campaigns

Agent-MD:用于有状态GCMC-MD模拟流程的带事件驱动升级机制的选择性大语言模型干预框架

Yijie Wang, Zhen-Yu Yin, Zhenheng Tang, Xiaowen Chu

机构 * The Hong Kong Polytechnic University(香港理工大学) The Hong Kong University of Science and Technology(香港科技大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

专题命中 规划决策 :agent(title,title_cn);workflow(abstract);分类 cs.AI

AI总结 Agent-MD框架将LLM推理选择性用于GCMC-MD分子模拟流程的构建与事件审查,结合确定性执行,在蒙脱石水蒸汽脱附模拟中完成多周期计算,识别问题并揭示体系依赖的低湿度响应,实现可复现的代理辅助分子模拟。

Comments 7 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10601 2026-07-14 cs.AI 新提交 91%

Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories

Agentic-DPO:从专家轨迹上的模仿到智能体策略优化

Yixiong Chen, Alan Yuille

机构 * Johns Hopkins University(约翰·霍普金斯大学)

专题命中 规划决策 :agentic(title,title_cn);agent(abstract);分类 cs.AI

AI总结 研究针对大语言模型智能体基于专家轨迹训练只学动作序列、难应对错误的问题,提出Agentic-DPO方法,通过转化专家轨迹为状态条件偏好监督,结合策略保持增强,实现低成本智能体策略优化,实验验证其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.15952 2026-06-16 cs.AI 版本更新 91%

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

基于Agent Rosetta的蛋白质设计:面向专业科学智能体的案例研究

Jacopo Teneggi, S. M. Bargeen A. Turzo, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar

机构 * Polymathic AI(多学科人工智能实验室) Center for Computational Biology, Flatiron Institute(计算生物学中心,Flatiron研究所) Google DeepMind(谷歌DeepMind) Center for Computational Mathematics, Flatiron Institute(计算数学中心,Flatiron研究所) New York University(纽约大学) Johns Hopkins University(约翰霍普金斯大学)

专题命中 规划决策 :agent(title,title_cn);autonomous agent(abstract);分类 cs.AI

AI总结 提出Agent Rosetta,将大语言模型与Rosetta软件环境结合,通过迭代优化实现用户定义的蛋白质设计目标,在规范氨基酸设计上匹配专家,在非规范残基设计上超越现有ML方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06448 2026-06-05 cs.AI 91%

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

Agent记忆:有状态长时任务工作负载的表征与系统影响

Yasmine Omri, Ziyu Gan, Zachary Broveak, Robin Geens, Zexue He, Alex Pentland, Marian Verhelst, Tsachy Weissman, Thierry Tambe

机构 * Massachusetts Institute of Technology(麻省理工学院) Stanford University(斯坦福大学) University of California, Berkeley(加州大学伯克利分校) MIT Media Lab(麻省理工学院媒体实验室)

专题命中 规划决策 :agent(title,title_cn);agentic(abstract);分类 cs.AI

AI总结 本文首次对LLM agent记忆系统进行系统级表征,提出四轴分类法,通过阶段感知分析框架评估10种代表性系统,并给出10条系统设计建议。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.03435 2026-06-03 cs.AI 91%

CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations

CP-Agent: 化学扰动下细胞形态学轮廓的上下文感知多模态推理

Yuxin Zhang, Yiyao Li, Ping Shu Ho, Simon See, Zhenqin Wu, Kevin Tsia

机构 * Department of Electrical and Computer Engineering, The University of Hong Kong(香港大学电子与计算机工程系) School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院) School of Biomedical Engineering, The University of Hong Kong(香港大学生物医学工程学院) Nvidia AI Technology Center(NVIDIA人工智能技术中心) Advanced Biomedical Instrumentation Centre(先进生物医学仪器中心)

专题命中 规划决策 :agent(title,title_cn);agentic(abstract);分类 cs.AI

AI总结 提出CP-Agent,一种基于上下文感知对齐模块CP-CLIP的多模态大语言模型,用于生成药物扰动下细胞形态变化的可解释机制性解释,实现高精度处理与机制区分(最大F1分数0.896),并整合工具使用与推理生成结构化报告以加速药物发现。

Comments ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16112 2026-05-20 cs.AI 91%

IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra

IR-Agent: 专家启发的LLM代理用于从红外光谱中解析分子结构

Heewoong Noh, Namkyeong Lee, Gyoung S. Na, Kibum Kim, Chanyoung Park

机构 * KAIST(韩国科学技术院) KRICT(韩国信息通信技术研究院)

专题命中 规划决策 :agent(title,title_cn);multi-agent(abstract);分类 cs.AI

AI总结 本文提出IR-Agent,一种新的多代理框架,用于从红外光谱中解析分子结构,通过模拟专家驱动的分析过程,提升结构解析的准确性。

Comments ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.04875 2026-04-07 cs.CV cs.AI cs.MM 91%

DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing

DIRECT:通过分层多智能体规划和意图引导编辑实现视频混剪创作

Ke Li, Maoliang Li, Jialiang Chen, Jiayu Chen, Zihao Zheng, Shaoqi Wang, Xiang Chen

机构 * School of Electronics Engineering and Computer Science, Peking University(北京大学电子工程与计算机科学学院) School of Computer Science, Peking University(北京大学计算机科学学院) Huazhong University of Science and Technology(华中科技大学)

专题命中 规划决策 :agent(title,abstract);multi-agent(title,abstract);planning(title);分类 cs.AI

AI总结 本文提出DIRECT框架,通过分层多智能体规划和意图引导编辑解决视频混剪中多模态协调问题,提出Mashup-Bench基准并验证了方法在客观和主观评估上的优越性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01357 2026-03-03 cs.AI 91%

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

ASTRA-bench: 通过个人用户上下文评估工具使用代理的推理与行动规划

Zidi Xiu, David Q. Sun, Kevin Cheng, Maitrik Patel, Josh Date, Yizhe Zhang, Jiarui Lu, Omar Attia, Raviteja Vemulapalli, Oncel Tuzel, Meng Cao, Samy Bengio

机构 * Apple(苹果公司)

专题命中 规划决策 :tool-use(title,abstract);planning(title,abstract);agent(title);分类 cs.AI

AI总结 ASTRA-bench通过模拟真实用户情境,评估AI代理在复杂个人上下文中进行推理与多步骤计划的能力,揭示当前模型在处理高复杂度任务时的性能瓶颈。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19304 2026-02-24 cs.RO cs.AI cs.HC cs.MA 91%

Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation

安全且可解释的多模态路径规划用于多智能体协作

Haojun Shi, Suyu Ye, Katherine M. Guerrerio, Jianzhi Shen, Yifan Yin, Daniel Khashabi, Chien-Ming Huang, Tianmin Shu

机构 * Johns Hopkins University(约翰霍普金斯大学)

专题命中 规划决策 :agent(title,abstract);planning(title,abstract);multi-agent(title);分类 cs.AI

AI总结 CaPE通过多模态路径规划实现安全且可解释的多智能体协作,利用视觉-语言模型和模型基于规划器确保路径调整的安全性和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏