AI Agent

TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving

TPS-Drive: 基于VLM的自动驾驶任务引导表示净化

Jiaxiang Li, Yumao Liu, Ke Ma

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） 纠错

专题命中 规划决策 ：agent(summary_cn,abstract)；planning(abstract)

AI总结 提出TPS-Drive框架，通过任务引导的表示净化（Agent-Centric Tokenizer）解决VLM在自动驾驶中的空间幻觉和表示干扰问题，实现精确的3D空间预测与安全规划。

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

GLM-5V-Turbo：迈向多模态代理的原生基础模型

V Team, Wenyi Hong, Xiaotao Gu, Ziyang Pan, Zhen Yang, Yuting Wang, Yue Wang, Yuanchang Yue, Yu Wang, Yanling Wang, Yan Wang, Xijun Liu, Wenmeng Yu, Weihan Wang, Wei Li, Shuaiqi Duan, Sheng Yang, Ruiliang Lv, Mingdao Liu, Lihang Pan, Ke Ning, Junhui Ji, Jinjiang Wang, Jing Chen, Jiazheng Xu, Jiale Zhu, Jiale Cheng, Ji Qi, Guobing Gan, Guo Wang, Cong Yao, Zijun Dou, Zihao Zhou, Zihan Wang, Zhiqi Ge, Zhijie Li, Zhenyu Hou, Zhao Xue, Zehui Wang, Zehan Qi, Zehai He, Yutao Zhang, Yusen Liu, Yukuo Cen, Yuchen Li, Yuan Wang, Yu Yang, Yongbin Liu, Yijian Lu, Yifan Xu, Yanzi Wang, Yanxiao Zhao, Yanfeng Wang, Yadong Xue, Yabo Xu, Xinyu Zhang, Xinyu Liu, Xiao Liu, Wenyi Zhao, Wenkai Li, Tianyu Tong, Tianshu Zhang, Shudan Zhang, Shengdong Yan, Qinkai Zheng, Mingde Xu, Licheng Bao, lat Long long, Jiaxing Xu, Jiaxin Fan, Jiawen Qian, Jiali Chen, Jiahui Lin, Jiadai Sun, Haozhi Zheng, Haoran Wang, Haochen Li, Hanyu Lai, Han Xu, Fan Yang, Dan Zhang, Da Yin, Chuangxin Zhao, Chengcheng Wu, Boyan Shi, Bowen Lv, Bowei Jia, Bo Li, Bin Chen, Baoxu Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang

机构 * Z.ai & Tsinghua University（Z.ai与清华大学） 纠错

专题命中 规划决策 ：agent(abstract)；tool use(abstract)；planning(abstract)；agentic(abstract)

AI总结 GLM-5V-Turbo旨在提升多模态代理的感知与执行能力，通过整合多模态感知作为推理、规划和工具使用的核心组件，实现跨异构上下文的高效处理。

Repeated Matching Games: An Empirical Framework

重复匹配游戏：一个经验框架

Pauline Corblet, Jeremy Fox, Alfred Galichon

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 本文提出一个动态匹配模型，扩展了Shapley和Shubik（1971）的静态模型，探讨了时间变化的 agent 类型分布和稳态均衡的存在性，并利用计量经济学冲击处理匹配异质性，通过两种算法计算稳态均衡并估计瑞典工程师的人力资本积累模型。

Comments The authors have identified potential inconsistencies in some of the proofs and wish to withdraw the paper while conducting a thorough re-evaluation

Neither Consent nor Property: A Policy Lab for Data Law

既非同意亦非财产：数据法的政策实验室

Haoyi Zhang, Tianyi Zhu

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 本文通过构建数据市场的Agent-Based模型，探讨数据法中同意与财产规则对福利的影响，发现将实质性损害责任转移给下游买家可最大化社会福利。

Acts of Configuration: Rethinking Provenance, Temporality and Legitimacy in Post-Mortem Agents

配置行为：重新思考死后代理的来源、时间和合法性

Kellie Yu Hui Sim, Pin Sym Foong, Darryl Lim, John-Henry Lim, Kenny Tsu Wei Choo

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

AI总结 本文通过工作坊探讨死后代理在决策能力丧失后如何配置，发现人们更倾向于基于第一方授权的有限代理，但时间因素促使代理在能力丧失后保持静止并影响后续使用。

Comments Accepted at DIS 2026 (PWiP). 5 pages, 2 figures

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

MiroThinker-1.7 与 H1：通过验证实现重型研究代理

MiroMind Team, S. Bai, L. Bing, L. Lei, R. Li, X. Li, X. Lin, E. Min, L. Su, B. Wang, L. Wang, L. Wang, S. Wang, X. Wang, Y. Zhang, Z. Zhang, G. Chen, L. Chen, Z. Cheng, Y. Deng, Z. Huang, D. Ng, J. Ni, Q. Ren, X. Tang, B. L. Wang, H. Wang, N. Wang, C. Wei, Q. Wu, J. Xia, Y. Xiao, H. Xu, X. Xu, C. Xue, Z. Yang, Z. Yang, F. Ye, H. Ye, J. Yu, C. Zhang, W. Zhang, H. Zhao, P. Zhu

机构 * MiroMind Team（MiroMind团队） 纠错

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

AI总结 本文提出MiroThinker-1.7和H1，通过结构化规划和验证机制提升多步推理能力，在复杂任务中实现高效可靠的研究代理。

Comments 23 pages

CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization

CodeV: 通过工具感知策略优化实现基于图像的代码推理

Xinhai Hou, Shaoyuan Xu, Manan Biyani, Moyan Li, Jia Liu, Todd C. Hollon, Bryan Wang

机构 * University of Michigan（密歇根大学） ； The Ohio State University（俄亥俄州立大学） 纠错

专题命中 规划决策 ：agent(abstract)；tool use(abstract)；tool-use(abstract)；agentic(abstract)

AI总结 CodeV通过工具感知策略优化提升视觉推理的忠实度，实现更高准确率和更可靠的工具使用。

A Survey on Large Language Model-based Agents for Statistics and Data Science

关于基于大型语言模型的统计与数据科学代理的综述

Maojun Sun, Ruijian Han, Binyan Jiang, Houduo Qi, Defeng Sun, Yancheng Yuan, Jian Huang

机构 * Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（数据科学与人工智能系，香港理工大学） ； Department of Applied Mathematics, The Hong Kong Polytechnic University（应用数学系，香港理工大学） 纠错

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

AI总结 本文综述了基于大型语言模型的数据科学代理的发展、能力和应用，探讨了其设计趋势及实际应用，并提出了未来研究方向。

Journal ref Am. Statist. (2025) 1-14

Your Ride, Your Rules: Psychology and Cognition Enabled Automated Driving Systems

Zhipeng Bao, Qianwen Li

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

Comments 32 pages, one colummns

ProRefine: Inference-Time Prompt Refinement with Textual Feedback

Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Isabelle Diana May-Xin Ng, Christopher M. Homan, Wei Wei

机构 * Center for Advanced AI, Accenture（高级人工智能研究中心，Accenture） ； Rochester Institute of Technology（罗切斯特理工学院） ； UC Berkeley（加州大学伯克利分校） 纠错

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

Comments Workshop on Efficient Reasoning at NeurIPS 2025

Improved Obstacle Avoidance for Autonomous Robots with ORCA-FLC

Justin London

机构 * Dept. of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； University of North Dakota（北达科他大学） 纠错

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

Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications

Wenxuan Wang, Zizhan Ma, Meidan Ding, Shiyi Zheng, Shengyuan Liu, Jie Liu, Jiaming Ji, Wenting Chen, Xiang Li, Linlin Shen, Yixuan Yuan

机构 * Renmin University of China（中国人民大学） ； The Chinese University of Hong Kong（香港中文大学） ； Shenzhen University（深圳大学） ； City University of Hong Kong（香港城市大学） ； Peking University（北京大学） ； Massachusetts General Hospital and Harvard Medical School（麻省总医院和哈佛医学院） 纠错

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

Augmenting Von Neumann's Architecture for an Intelligent Future

Rajpreet Singh, Vidhi Kothari

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

Comments 6 pages, 2 figures

Quantum Agents

Eldar Sultanow, Madjid Tehrani, Siddhant Dutta, William J Buchanan, Muhammad Shahbaz Khan

专题命中 规划决策 ：agent(abstract)；autonomous agent(abstract)；planning(abstract)；agentic(abstract)

Comments 45 Pages, 16 figures, 3 Tables

Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability

Zishen Wan, Jiayi Qian, Yuhang Du, Jason Jabbour, Yilun Du, Yang Katie Zhao, Arijit Raychowdhury, Tushar Krishna, Vijay Janapa Reddi

专题命中 规划决策 ：agent(abstract)；AI agent(abstract)；autonomous agent(abstract)；planning(abstract)

Comments 2025 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)

AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

Brendan Hogan, Anmol Kabra, Felipe Siqueira Pacheco, Laura Greenstreet, Joshua Fan, Aaron Ferber, Marta Ummus, Alecsander Brito, Olivia Graham, Lillian Aoki, Drew Harvell, Alex Flecker, Carla Gomes

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

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

Jianliang He, Siyu Chen, Fengzhuo Zhang, Zhuoran Yang

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

Comments 47 pages, accepted by ICML 2024

Multi-Robot Local Motion Planning Using Dynamic Optimization Fabrics

Saray Bakker, Luzia Knoedler, Max Spahn, Wendelin Böhmer, Javier Alonso-Mora

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

Comments 6 pages + 1 page references, 2 tables, 4 figures, preprint version to accepted paper to IEEE International Symposium on Multi-Robot & Multi-Agent Systems, Boston, 2023

Social Coordination and Altruism in Autonomous Driving

Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah

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

Comments Under Review in an IEEE Journal

Predicted Composite Signed-Distance Fields for Real-Time Motion Planning in Dynamic Environments

Mark Nicholas Finean, Wolfgang Merkt, Ioannis Havoutis

专题命中 规划决策 ：planning(title,abstract)

Comments International Conference on Automated Planning and Scheduling (ICAPS), 2021

Journal ref Proceedings of the International Conference on Automated Planning and Scheduling, 2021, 31(1), 616-624

Data-Efficient Learning of High-Quality Controls for Kinodynamic Planning used in Vehicular Navigation

Seth Karten, Aravind Sivaramakrishnan, Edgar Granados, Troy McMahon, Kostas E. Bekris

专题命中 规划决策 ：planning(title,abstract)

Comments Presented at the Machine Learning for Motion Planning (MLMP) Workshop at ICRA 2021, Xi'an, China

Journal ref Machine Learning for Motion Planning (MLMP) Workshop at ICRA 2021, Xi'an, China

Barrier Functions for Multiagent-POMDPs with DTL Specifications

Mohamadreza Ahmadi, Andrew Singletary, Joel W. Burdick, Aaron D. Ames

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

Comments arXiv admin note: text overlap with arXiv:1903.07823

Grounding Language for Transfer in Deep Reinforcement Learning

Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

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

Comments JAIR 2018

Scalable Asymptotically-Optimal Multi-Robot Motion Planning

Andrew Dobson, Kiril Solovey, Rahul Shome, Dan Halperin, Kostas E. Bekris

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

Comments 8 pages, 12 figures, submitted to the first International Symposium on Multi-Robot and Multi-Agent Systems (MRS)

Augmenting Agent Platforms to Facilitate Conversation Reasoning

David Lillis, Rem W. Collier`

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

Journal ref In Languages, Methodologies, and Development Tools for Multi-Agent Systems - Third International Workshop, LADS 2010, Revised Selected Papers, Lecture Notes in Computer Science vol. 6822, pp. 56--75. Springer Berlin Heidelberg, 2011

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe

解析长期任务工具使用强化学习：全面指南

Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng

机构 * The Chinese University of Hong Kong（香港中文大学） ； IDEA Research（IDEA研究院） ； University of Macau（澳门大学） 纠错

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

AI总结 本文通过TravelPlanner测试环境，系统研究了强化学习在复杂多轮任务中的应用，提出7条关键发现，包括奖励设计、模型规模、数据组成等五个维度，最终实现超越领先LLM的性能。

Comments Codes are available at https://github.com/WxxShirley/Agent-STAR

Cognitive Homeostatic Agents

Amol Kelkar

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

Comments Accepted at AAMAS2021 Blue Sky Ideas Track

Journal ref In Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), Online, May 3-7, 2021, IFAAMAS, 5 pages

Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models

面向多模态大语言模型的符合规则的视觉空间规划

Yu Chen, Ting Lei, Yaoyi Li, Jia Cai, Zhecen Wu, Yang Liu

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所） ； Yinwang Intelligent Technology Co., Ltd（银湾智能科技有限公司） 纠错

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

AI总结 该研究针对多模态大语言模型的规则遵循空间规划问题，构建了RuleMaze基准，提出语言-逻辑-函数混合方法和解耦多模态规划（DMP），提升了规则遵循度与规划成功率。

SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

SAPO：用于智能体强化学习的单回滚自回归策略优化

Dayang Liang, Lang Feng, Bo An, Yunlong Liu

机构 * Xiamen University（厦门大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

AI总结 本研究针对智能体强化学习现有方法的三大局限，提出SAPO框架，其共享策略与价值函数的自回归主干，结合广义优势估计器，在ALFWorld、WebShop任务上性能优于PPO和GRPO，内存与计算效率更高。

PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty

PO-PDDL: 从视觉演示中学习符号化POMDP以实现不确定性下的机器人规划

Wenjing Tang, Xuanjin Jin, Yuan Liu, Renming Huang, Cewu Lu, Panpan Cai

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai Innovation Institute（上海创新研究院） 纠错

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

AI总结 提出PO-PDDL符号化POMDP框架，通过从机器人执行视频中重建潜在状态轨迹、识别部分可观测性并学习随机转移与观测模型，实现不确定性下的鲁棒任务规划。