AI Agent

Explanation as Question Answering based on a Task Model of the Agent's Design

Ashok Goel, Harshvardhan Sikka, Vrinda Nandan, Jeonghyun Lee, Matt Lisle, Spencer Rugaber

专题命中 Agent评测 ：agent(title,abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Comments 7 Pages, 10 Figures, IJCAI Explainable AI Workshop

Agent Smith: Teaching Question Answering to Jill Watson

Ashok Goel, Harshvardhan Sikka, Eric Gregori

专题命中 Agent评测 ：agent(title,abstract)；AI agent(abstract)；分类 cs.AI、cs.LG

Comments 11 Pages, 9 Figures

Competency Assessment for Autonomous Agents using Deep Generative Models

Aastha Acharya, Rebecca Russell, Nisar R. Ahmed

专题命中 Agent评测 ：autonomous agent(title,abstract)；agent(abstract)；分类 cs.AI、cs.LG

An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations

Glenn Maguire, Nicholas Ketz, Praveen Pilly, Jean-Baptiste Mouret

专题命中 Agent评测 ：autonomous agent(title,abstract)；agent(abstract)；分类 cs.AI、cs.LG

AGENT: A Benchmark for Core Psychological Reasoning

Tianmin Shu, Abhishek Bhandwaldar, Chuang Gan, Kevin A. Smith, Shari Liu, Dan Gutfreund, Elizabeth Spelke, Joshua B. Tenenbaum, Tomer D. Ullman

专题命中 Agent评测 ：agent(title,abstract)；planning(abstract)；分类 cs.AI、cs.LG

Comments ICML 2021, 12 pages, 7 figures

Learning of Behavior Trees for Autonomous Agents

Michele Colledanchise, Ramviyas Parasuraman, Petter Ögren

专题命中 Agent评测 ：autonomous agent(title,abstract)；agent(abstract)；分类 cs.AI、cs.LG

Journal ref IEEE Transactions on Games ( Volume: 11 , Issue: 2 , June 2019 )

VAmoS Bench: Voice Agent Simulation Bench

VAmoS Bench：语音智能体仿真基准

Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan, Sun Kim, Victor Shih, Mehdi Jamei, Andi Partovi

机构 * Veris AI（维瑞斯人工智能公司） 纠错

专题命中 Agent评测 ：agent(title,abstract)；分类 cs.AI

AI总结 该研究推出 VAmoS Bench 语音智能体仿真基准，针对现有基准无法评估语音智能体独立处理电话呼叫能力的空白，在金融服务场景中端到端评估完整语音智能体系统，支持动态排行榜。

Comments 12 pages, 3 figures, 2 tables. Agent implementations: https://github.com/veris-ai/riley-agent

ProofCouncil: An LLM Agent for Solving Open Mathematical Problems

ProofCouncil：用于解决开放性数学问题的语言模型智能体

Johannes Schmitt, Tim Gehrunger, Jasper Dekoninck, Gergely Bérczi, Uri Kreitner, Liam Price, David Holmes

机构 * ETH Zurich（苏黎世联邦理工学院） ； Aarhus University（奥胡斯大学） ； Leiden University（莱顿大学） 纠错

专题命中 Agent评测 ：agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 研究旨在提升大型语言模型解决数学开放性问题的性能，介绍了ProofCouncil智能体，它采用作者-评论家架构，在FirstProof挑战及其他问题测试中表现出色，还介绍了其开发及相关构建库并开源。

Comments 25 pages, 7 figures. ProofCouncil appears as System A (IMProofBench ProofCouncil) in the official FirstProof second-batch report (arXiv:2606.18119). Code and agent-building library: https://github.com/eth-sri/proof-council

Anchor: Mitigating Artifact Drift in Agent Benchmark Generation

Anchor：缓解智能体基准生成中的工件漂移

Maksim Ivanov, Abhijay Rana

机构 * Agentic Labs 纠错

专题命中 Agent评测 ：agent(title,abstract)；AI agent(abstract)；分类 cs.AI；agentic(comments)

AI总结 提出Anchor管道，通过约束优化程序联合生成指令、环境、真值解和验证器，解决基准生成中的工件漂移问题，并构建ERP-Bench基准评估前沿模型性能。

Comments Accepted to RLEval '26 (Workshop at ACM Conference on AI and Agentic Systems 2026)

AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation

AnomalyClaw：通过工具引导的反驳实现通用视觉异常检测代理

Xi Jiang, Yinjie Zhao, Zesheng Yang, Feng Zheng

机构 * Department of Computer Science and Engineering, Southern University of Science and Technology (SUSTech), Shenzhen, China（南方科技大学计算机科学与工程系，深圳，中国） ； School of EEE, Nanyang Technological University (NTU), Singapore（南洋理工大学电子工程学院，新加坡） ； CFAR, Agency for Science, Technology and Research (A*STAR), Singapore（科技研究局（A*STAR）的CFAR，新加坡） 纠错

专题命中 Agent评测 ：agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 本文提出AnomalyClaw，一种无需训练的视觉异常检测代理，通过多轮反驳过程提升异常判断。在CrossDomainVAD-12基准上，AnomalyClaw在多个模型上均取得显著提升，且引入自演化扩展提升模型性能。

Comments We release the agent, the benchmark, and the analysis artifacts at https://github.com/jam-cc/AnomalyClaw

MedPAO: A Protocol-Driven Agent for Structuring Medical Reports

Shrish Shrinath Vaidya, Gowthamaan Palani, Sidharth Ramesh, Velmurugan Balasubramanian, Minmini Selvam, Gokulraja Srinivasaraja, Ganapathy Krishnamurthi

机构 * Department of Data Science and AI, IIT Madras, India（数据科学与人工智能系，印度理工学院马德拉斯学院） ； Department of Engineering Design, IIT Madras, India（工程设计系，印度理工学院马德拉斯学院） ； LoveForm Health Technologies, India（LoveForm健康科技公司，印度） ； Department of Radiology and Imaging Sciences, Sri Ramachandra Institute of Higher Education and Research, India（放射学与成像科学系， Sri Ramachandra高等教育与研究学院，印度） ； Department of Neuro and Interventional Radiology, Sri Ramachandra Institute of Higher Education and Research, India（神经放射学与介入放射学系，Sri Ramachandra高等教育与研究学院，印度） 纠错

专题命中 Agent评测 ：agent(title,abstract)；agentic(abstract,comments)；分类 cs.AI

Comments Paper published at "Agentic AI for Medicine" Workshop, MICCAI 2025

Journal ref Lecture Notes in Computer Science, vol 16147, 2025. Springer, Cham

Towards General Agentic Intelligence via Environment Scaling

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

机构 * Tongyi Lab（通义实验室） ； Alibaba Group（阿里巴巴集团） 纠错

专题命中 Agent评测 ：agentic(title,abstract)；agent(abstract,comments)；分类 cs.CL

Comments https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/

Oversight Structures for Agentic AI in Public-Sector Organizations

Chris Schmitz, Jonathan Rystrøm, Jan Batzner

机构 * Centre for Digital Governance, Hertie School（数字治理中心，赫尔姆斯学校） ； Oxford Internet Institute, University of Oxford（牛津互联网研究所，牛津大学） ； Weizenbaum Institute Berlin, Germany（贝伦贝格Weizenbaum研究所） ； Technical University Munich, Germany（慕尼黑技术大学） 纠错

专题命中 Agent评测 ：agentic(title,abstract)；agent(abstract,journal_ref)；分类 cs.AI

Comments To appear at REALM@ACL2025

Journal ref Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025), pages 298-308, Vienna, Austria. Association for Computational Linguistics

Agent-as-a-Judge: Evaluate Agents with Agents

Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber

专题命中 Agent评测 ：agent(title,abstract)；agentic(abstract)；分类 cs.AI

Comments The project can be found at https://github.com/metauto-ai/agent-as-a-judge. The dataset is released at https://huggingface.co/DEVAI-benchmark

Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning

Tong Niu, Weihao Zhang, Rong Zhao

专题命中 Agent评测 ：agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG；autonomous agent(journal_ref)

Journal ref International Conference on Autonomous Agents and Multiagent Systems 2024

Conditional Multi-Event Temporal Grounding in Long-Form Video

长视频中的条件多事件时间定位

Yuanhao Zou, Arthad Kulkarni, Lucas Tonanez, Lincoln Spencer, Guangyu Sun, Tianxingjian Ding, Andong Deng, Yi Li, Shuangjun Liu, Yuan Li, Dashan Gao, Ning Bi, Taotao Jing, Shuai Zhang, Chen Chen

机构 * University of Central Florida（中佛罗里达大学） ； Qualcomm AI Research（高通人工智能研究院） 纠错

专题命中 Agent评测 ：agent(summary_cn,abstract)；agentic(abstract)

AI总结 提出CoMET-Bench基准和CoMET-Agent框架，解决长视频中基于组合时空条件定位所有事件的任务，F1@0.5提升6.1%。

Autonomous Agent Behaviour Modelled in PRISM -- A Case Study

基于PRISM的自主代理行为建模——一个案例研究

Ruth Hoffmann, Murray Ireland, Alice Miller, Gethin Norman, Sandor Veres

机构 * University of Glasgow（格拉斯哥大学） ； University of Sheffield（谢菲尔德大学） 纠错

专题命中 Agent评测 ：agent(title)；autonomous agent(title)

AI总结 本文提出了一种抽象的自主性定义，用于建模自主场景，并通过小规模仿真模型推断定量数据，以验证无人飞行器在自主场景中的行为。

Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis

通过技能级评估与诊断解构多模态语言模型的具身能力

Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Yizhe Zhu, Shiji Xin, Yijian Huang, Boce Hu, Kai Cheng, Peiheng Wang, Jiazheng Liu, Jiayi Zhang, Yizhe Zhu, Wenqing Wang, Yiran Qin, Haojie Huang, Lawson L. S. Wong

机构 * Northeastern University, Boston, MA, USA ； The Chinese University of Hong Kong, Hong Kong, China ； Peking University, Beijing, China ； Westlake University, Hangzhou, China ； Harvard University, Cambridge, MA, USA ； Purdue University, West Lafayette, IN, USA ； University of Oxford, Oxford, United Kingdom 纠错

专题命中 Agent评测 ：agent(summary_cn,abstract)；planning(abstract)

AI总结 本文提出BEAR基准，通过分解具身任务为14个原子技能进行细粒度评估，发现感知能力是推理失败的主要瓶颈，并提出BEAR-Agent多模态对话代理，显著提升具身技能性能。

Comments Accepted to ICML 2026

Is Your Driving World Model an All-Around Player?

你的驾驶世界模型是全能选手吗？

Lingdong Kong, Ao Liang, Tianyi Yan, Hongsi Liu, Wesley Yang, Ziqi Huang, Xian Sun, Wei Yin, Jialong Zuo, Yixuan Hu, Dekai Zhu, Dongyue Lu, Youquan Liu, Guangfeng Jiang, Linfeng Li, Xiangtai Li, Long Zhuo, Lai Xing Ng, Benoit R. Cottereau, Changxin Gao, Liang Pan, Wei Tsang Ooi, Ziwei Liu

专题命中 Agent评测 ：agent(summary_cn,abstract)；planning(abstract)

AI总结 本文提出WorldLens基准测试，评估驾驶世界模型在视觉和行为真实性方面的综合表现，揭示现有模型在不同维度上的不足，并引入WorldLens-26K和WorldLens-Agent提升评估的可解释性。

Comments CVPR 2026 VideoWorldModel Workshop; Project Page at https://worldbench.github.io/worldlens GitHub at https://github.com/worldbench/WorldLens

E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task

E2EDev：端到端软件开发任务中大语言模型的基准测试

Jingyao Liu, Chen Huang, Zhizhao Guan, Wenqiang Lei, Yang Deng

机构 * College of Computer Science, Sichuan University（四川大学计算机学院） ； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所） ； CHAT NLP Group, Singapore Management University（新加坡国立管理大学CHAT NLP组） ； Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China（教育部长机器学习与产业智能工程研究中心） 纠错

专题命中 Agent评测 ：agent(abstract,abstract_cn)；multi-agent(abstract,abstract_cn)；分类 cs.AI、cs.CL、cs.SE

AI总结 本文提出E2EDev基准，基于行为驱动开发原则，通过模拟真实用户交互评估端到端软件开发框架的能力，揭示现有方法在解决复杂任务中的不足。

Comments Accepted to ACL 2026 main

The relationship between general equilibrium models with infinite-lived agents and overlapping generations models, and some applications

一般均衡模型中无限寿命 agent 与重叠世代模型的关系及其一些应用

Ngoc-Sang Pham

专题命中 Agent评测 ：agent(title_cn,summary_cn)

AI总结 本文研究了无限寿命 agent 一般均衡模型与重叠世代模型的关系，证明了两者在均衡条件下的相互转化，并探讨了其在经济应用中的意义。

Space Debris Removal using Nano-Satellites controlled by Low-Power Autonomous Agents

利用低功耗自主代理控制的纳米卫星进行太空碎片清除

Dennis Christmann, Juan F. Gutierrez, Sthiti Padhi, Patrick Plörer, Aditya Takur, Simona Silvestri, Andres Gomez

机构 * Institut für Datentechnik, TU Braunschweig（数据技术研究所， Braunschweig 技术大学） ； Institut für Raumfahrtsysteme, TU Braunschweig（航天系统研究所， Braunschweig 技术大学） 纠错

专题命中 Agent评测 ：autonomous agent(title,abstract)；agent(abstract,comments)；multi-agent(comments)

AI总结 本文提出利用低功耗自主代理控制的纳米卫星群，用于安全清除太空碎片，通过实验验证其可行性与能耗效率。

Comments This is an open-access, author-archived version of a manuscript published in European Conference on Multi-Agent Systems 2024

CSP: A Simulator For Multi-Agent Ranking Competitions

Tommy Mordo, Tomer Kordonsky, Haya Nachimovsky, Moshe Tennenholtz, Oren Kurland

专题命中 Agent评测 ：agent(title)；multi-agent(title)

On Risk Evaluation and Control of Distributed Multi-Agent Systems

Aray Almen, Darinka Dentcheva

专题命中 Agent评测 ：agent(title)；multi-agent(title)

Fast Agent-Based Simulation Framework with Applications to Reinforcement Learning and the Study of Trading Latency Effects

Peter Belcak, Jan-Peter Calliess, Stefan Zohren

专题命中 Agent评测 ：agent(title,abstract)；multi-agent(abstract,comments)

Comments Presented at the International Workshop on Multi-Agent Systems and Agent-Based Simulation (MABS@AAMAS) 2021, 12 pages, 8 figures

An Algorithm for Exact Numerical Age-of-Information Evaluation in Multi-Agent Systems

Richard Schoeffauer, Gerhard Wunder

专题命中 Agent评测 ：agent(title)；multi-agent(title)

Towards a Very Large Scale Traffic Simulator for Multi-Agent Reinforcement Learning Testbeds

Zijian Hu, Chengxiang Zhuge, Wei Ma

专题命中 Agent评测 ：agent(title)；multi-agent(title)

Comments IJCAI 2021 Reinforcement Learning for Intelligent Transportation Systems (RL4ITS) Workshop

How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?

Tucker Hybinette Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette, David Byrd

专题命中 Agent评测 ：agent(title,abstract)；multi-agent(abstract,journal_ref)

Journal ref Presented at the 2019 ICML Workshop on AI in Finance: Applications and Infrastructure for Multi-Agent Learning. Long Beach, CA

An Appraisal Transition System for Event-driven Emotions in Agent-based Player Experience Testing

Saba Gholizadeh Ansari, I. S. W. B. Prasetya, Mehdi Dastani, Frank Dignum, Gabriele Keller

专题命中 Agent评测 ：agent(title,abstract)；分类 cs.AI、cs.SE；autonomous agent(comments)；multi-agent(comments)

Comments This is a preprint of an article with the same title, accepted in 9th International Workshop on Engineering Multi-Agent Systems (EMAS 2021) which was held as a part of 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)

TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments

TimeSage-EV：面向动态环境下智能体时间序列分析的实时基准测试集

Qingren Yao, Yaxuan Kong, Yuqi Nie, Yichen Li, Stefan Zohren, Anna Vettoruzzo, Qingsong Wen, Ming Jin, Joaquin Vanschoren

机构 * Eindhoven University of Technology（埃因霍温理工大学） ； University of Oxford（牛津大学） ； VulpiVox Intelligence（VulpiVox智能公司） ； Squirrel Ai Learning（Squirrel AI学习公司） ； Griffith University（格里菲斯大学） 纠错

专题命中 Agent评测 ：agentic(title,abstract)；agent(abstract)；分类 cs.AI

AI总结 针对现有时间序列基准未评估时间有效性等问题，推出动态环境智能体时间序列分析基准TimeSage-EV，含多领域真实场景，实验揭示模型性能差距及失败模式，提供研究资源。