AI Agent

SoundscapeAgent: Agentic Soundscape Construction for Controllable Synthesis and Scalable Audio-Language Supervision

SoundscapeAgent：用于可控合成和可扩展音频-语言监督的智能音景构建

Hao Zhang, Yiwen Zhao, Yixuan Zhang, Yiwen Shao, Steve Yves

机构 * Tencent（腾讯） 纠错

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

AI总结 提出智能音景构建框架SoundscapeAgent，基于大语言模型的智能体将用户意图转化为场景计划，经多步骤实现可控音频合成与可扩展音频-语言数据构建，在生成性能及下游音频推理方面表现出色。

Comments Submitted to SLT 2026

Stochastic Multi-Objective Kinodynamic Planning Against Adversaries

针对对手的随机多目标运动动力学规划

Thomas Marshall Vielmetti, Daniel Cherenson, Dimitra Panagou

机构 * University of Michigan（密歇根大学） 纠错

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

AI总结 研究在含随机混合对手环境下的多目标运动动力学规划，核心方法是将规划空间转移到闭环策略序列，通过蒙特卡洛粒子展开评估风险，引入SMO-RRT和SMO-SST算法，推导有限样本界，实现概率安全规划。

Comments 8 pages, 1 figure, accepted to CDC 2026

FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents

FinanceComplexQA：对工业级金融文档进行智能体推理的基准测试

Xianfu Cheng, Shiwei Zhang, Jiyu Zhao, Jian Yang, Xinyuan Wang, Ming Zhou, Weixiao Zhou, Xiangyuan Guan, Xiang Li, Zhenhe Wu, Ziyi Ni, Zhoujun Li, Bingjing Xu

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

AI总结 研究针对金融文档智能体推理性能差异问题，设计Finance-LaTeX SKILL生成金融文档和问答对，引入FinanceComplexQA基准测试，对领先系统和工具全面评估，通过分析失败案例研究其在多方面的能力。

Comments 27 pages, 9 tables, 2 figures

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

WAR：用于同步智能体强化学习的工作负载感知展开

Ryan Xu, Atlas Zhao, David Bao, Frank Du

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

AI总结 研究针对智能体强化学习中展开成为系统瓶颈的问题，提出工作负载感知展开系统WAR，通过联合优化解码和调度加速同步智能体RL，在不同负载下提高吞吐量，消除主要展开瓶颈，为长上下文智能体训练提供实用路径。

PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution

PhyAgentOS：一种用于具身智能体的自进化操作系统，具有解耦的认知规划和物理执行

Yang Liu, Weixing Chen, Xinshuai Song, Tao Pu, Siwen Mo, Yongjie Bai, Zihao Chen, Qianran Sun, Liruo Zhong, Ying Shen, Liang Lin

机构 * X-Era Lab（X-Era实验室） ； HCP Lab, Sun Yat-sen University（中山大学HCP实验室） ； Peng Cheng Laboratory（鹏城实验室） 纠错

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

AI总结 研究为具身智能体提出PhyAgentOS操作系统，其以会话为最小调度单位，用文件系统解耦认知与物理执行，通过会话验证器区分执行与任务完成，经认知记忆整合结果，有分层安全约束，在多模型和实体上验证并优于其他系统。

SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification

SingGuard-NSFA：通过生成式推理和实时分类实现的可扩展智能体人工智能护栏

SingGuard Team

机构 * Ant Group（蚂蚁集团） 纠错

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

AI总结 研究针对智能体人工智能系统操作威胁，提出NSFA分类法构建基准套件，开发双模式方法，发布四个不同参数模型，在基准测试和跨源评估中表现出色，证明方法可扩展性与通用性。

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

保持策略梯度主导：面向长程工具使用智能体的兄弟引导信用蒸馏

Tianyu Ding, Jianhong Xin, Juan Pablo De la Cruz Weinstein

机构 * Amazon Web Services（亚马逊云服务） 纠错

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

AI总结 针对长程工具使用强化学习中轨迹级优势信号稀疏的问题，提出兄弟引导信用蒸馏（SGCD），通过动态采样成功与失败轨迹、外部LLM对比生成逐步信用参考，实现密集信用分配，在AppWorld和τ³-airline任务上显著提升性能。

Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing

用于多模态理解、生成和编辑的认知结构多模态智能体

Feng Wang, Canmiao Fu, Zhipeng Huang, Chen Li, Jing Lyu, Ge Li

机构 * Peking University（北京大学） ； Tencent Inc（腾讯公司） 纠错

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

AI总结 研究针对统一多模态模型在长时多模态对话中的局限，提出认知结构多模态智能体，通过外化视觉信息等方式改进。开发统一场景引擎，构建评估基准。实验显示该智能体检索准确率高、推理时间减半，还介绍了工具包，为长时多模态智能体提供新范式。

Comments 16 pages, 7 figures, 8 tables. Project page: https://caseclose.github.io/cma-harness/ Code: https://github.com/caseclose/cma-harness

A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving

一种用于自动驾驶的可靠上下文感知和时间规划框架

Argho Dey, Yunfei Yin, Swachha Ray, Md Minhazul Islam, Zheng Yuan, Sijing Xiong, Hongyu Liu, Zhiqiu Huang

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

AI总结 研究自动驾驶中车载传感退化时的可靠感知与规划问题，提出RCT-AD框架，通过显式建模特征质量和时间一致性，经可靠上下文感知模块和时间轨迹规划器等提升感知、预测及规划能力。

Comments Submitted to IEEE Transactions on Intelligent Transportation Systems. 12 pages, 6 figures

ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI

ACE-Brain-0.5：用于物理智能体人工智能的统一具身基础模型

Brain Team, Ziyang Gong, Haoming Gu, Zehang Luo, Tianyi Zhang, Tao Tao, Yixiao Chi, Zhe Liu, Lingsi Zhu, Jingyuan Liu, Anke Tang, Songze Li, Yilun Kong, Ningjing Liu, Tianyu Zhu, Yunpeng Qing, Shuang Luo, Xiang Liu, Shi Fu, Dawei Nie, Sixiang Liu, Zhexi Wen, Feng Pan, Xiaofeng Wang, Zhi Hou, Chunxiao Liu, Xue Yang, Junchi Yan, Hengshuang Zhao, Dacheng Tao, Xiaogang Wang

机构 * ACE-Brain Team（ACE-Brain团队） 纠错

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

AI总结 研究针对具身人工智能从模块向物理智能体发展的问题，提出ACE-Brain-0.5统一基础模型，通过耦合的五个功能及SSR+等方法，提升空间感知等能力，在多基准测试中有进步。

PowerDAG: Supervisory Agentic AI System for Automating Distribution Grid Analysis

PowerDAG：用于自动化配电网络分析的可靠代理AI系统

Emmanuel O. Badmus, Amritanshu Pandey

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

AI总结 本文提出PowerDAG，一种用于自动化复杂配电网络分析的代理AI系统，通过自适应检索和即时监督机制提升可靠性，实验显示其在未见查询上表现优异，优于现有基线方法。

Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

组图策略优化用于长程智能体强化学习

Yunan Wang, Minghui Song, Zihan Zhang, Shaohan Huang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

机构 * Peking University（北京大学） ； Microsoft Corporation（微软公司） 纠错

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

AI总结 提出G2PO算法，通过构建全局状态转移图并引入组聚合状态值估计和边中心优势估计，解决长程智能体强化学习中的奖励稀疏和信用分配粗粒度问题，在WebShop等基准上显著提升成功率。

Task Allocation and Motion Planning in Dynamic, Cluttered Environments via CBBA and Graphs of Convex Sets

动态杂乱环境下的任务分配与运动规划：基于CBBA与凸集图

Matthew D. Osburn, Cameron K. Peterson, John L. Salmon

机构 * Electrical and Computer Engineering（电气与计算机工程系） ； Mechanical Engineering（机械工程系） 纠错

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

AI总结 针对动态杂乱环境中的多智能体任务规划，提出结合凸集图（GCS）进行轨迹优化与共识捆绑算法（CBBA）进行分布式任务分配的方法，实现安全高效的轨迹规划和任务协调。

Comments 15 pages single column, 10 figures, AIAA-Scitech 2027 Submission

Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems

Green SARC：面向代理型AI系统的预测性成本与碳治理

Gaston Besanson

机构 * Universidad Torcuato Di Tella（托库托迪泰拉大学） 纠错

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

AI总结 提出Green SARC框架，通过架构级治理在代理循环中强制执行成本与碳预算，理论贡献包括预测性执行点，实验证明门控机制实现0%超支，端到端节省47-55%。

Comments 19 figures. Code: https://github.com/besanson/Greensarc -- Software DOI: https://doi.org/10.5281/zenodo.20692196

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Nemotron 3 Ultra: 开放、高效的混合专家Mamba-Transformer模型用于智能体推理

NVIDIA, :, Aaron Blakeman, Aaron Thomas, Aastha Jhunjhunwala, Abhibha Gupta, Abhinav Khattar, Adam Rajfer, Adi Renduchintala, Adil Asif, Aditya Vavre, Adriana Flores Miranda, Ahmad Bilal, Aileen Zaman, Ajay Hotchandani, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Alex Gronskiy, Alex Kondratenko, Alex Steiner, Alex Ye, Alexander Bukharin, Alexandre Milesi, Ali Taghibakhshi, Alice Gatti, Alisa Liu, Alok Kumar, Amar Phanishayee, Ameya Sunil Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Anahita Bhiwandiwalla, Ananth Subramaniam, Andrea Santilli, Andrew Fulks, Andrew McHarg, Andrew Tao, Andrii Skliar, Anjulie Agrusa, Ankur Srivastava, Ankur Verma, Anna Shors, Anna Warno, Antoni-Joan Solergibert I Llaquet, Arham Mehta, Arkadiusz Nowaczynski, Arti Jain, Ashwath Aithal, Ashwin Poojary, Asif Ahamed, Asit Mishra, Asma Kuriparambil Thekkumpate, Atefeh Sohrabizadeh, Avinash Kaur, Avinash Vem, Ayush Dattagupta, Barath Subramaniam Anandan, Bardiya Sadeghi, Ben Lanir, Benedikt Schifferer, Besmira Nushi, Bilal Kartal, Bill Thiede, Bita Darvish Rouhani, Bo Deng, Bob Schatz, Boris Ginsburg, Boxin Wang, Brad Nemire, Brandon Norick, Brian Dang, Brian Westphal, Brian Yu, Brucek Khailany, Bryan Catanzaro, Carlo del Mundo, Caryln Aarish, Chankyu Lee, Chantal Hwang, Charbel Sakr, Charles Wang, Charlie Truong, Chen Cui, Cheng Cheng, Cheng-Ping Hsieh, Chenghao Zhang, Chenhui Deng, Chintan Patel, Chris Alexiuk, Christian Cosgrove, Christian Munley, Christine Harvey, Christopher Parisien, Chunyang Shen, Coco Li, Collin Neale, Cynthia Gao, Cyril Meurillon, Dan Gil, Dan Su, Dan Zhao, Dane Corneil, Daniel Afrimi, Daniel Egert, Daniel Korzekwa, Daniel Lo, Daniel Machlab, Daniel Serebrenik, Daniil Sorokin, Daria Gitman, Daria Levy, Darko Stosic, David Mosallanezhad, David Yu, Davit Karamyan, Deena Donia, Deep Debroy, Deepak Narayanan, Devin O'Kelly, Dheeraj Peri, Dhruv Nathawani, Di, Wu, Dima Rekesh, Divyanshu Kakwani, Donald Plummer, Dong Anh, Dongfeng Yu, Dongfu Jiang, Donnie Kim, Dorrin Poorkay, Duncan Riach, Dusan Stosic, Dustin VanStee, Eavan Meng, Edgar Minasyan, Edward Lin, Eileen Margaret Peters Long, Elad Sarafin, Elad Segal, Elena Lantz, Ellie Evans, Elliott Ning, Eric Chung, Eric Harper, Eric Pham-Hung, Eric Tramel, Eric Yang, Erick Galinkin, Erik Pounds, Erika Goncalves Goncalves, Evan Briones, Evan Wu, Evelina Bakhturina, Evgeny Tsykunov, Ewa Dobrowolska, Faisal Ladhak, Farzan Memarian, Fay Wang, Fei Jia, Felipe Soares, Felipe Vieira Frujeri, Feng Chen, Fengguang Lin, Ferenc Galko, Frank Sun, Frankie Siino, Frida Hou, Gal Hubara Agam, Gal Kaplun, Gantavya Bhatt, Gargi Prasad, Garvit Kulshreshtha, George Armstrong, Gerald Shen, Giulio Borghesi, Gordana Neskovic, Gorkem Batmaz, Grace Lam, Greg Mason, Greg Pauloski, Grigor Nalbandyan, Grzegorz Chlebus, Grzegorz Karch, Guan-Ting Liu, Guoming Zhang, Guyue Huang, Haggai Maron, Haifeng Qian, Haim Elisha, Haoxing Ren, Haran Kumar Shiv Kumar, Haribhau Hud, Harris Nover, Harrison Saturley Hall, Hayate Iso, Helen Ngo, Herbert Hum, Herman Sahota, Hexin Wang, Himanshu Soni, Hovhannes Tamoyan, Hua Li, Huanhuan Chen, Hui Li, Hui Wang, Huy Nguyen, Ian Chiles, Ido Galil, Ido Shahaf, Igor Gitman, Igor Shovkun, Ilya Loshchilov, Ingo Guehring, Itamar Schen, Itay Levy, Itay Neeman, Ivan Moshkov, Izik Golan, Izzy Putterman, Jaemin Choi, Jakub Slowikowski, Jan Kautz, Jane Polak Scowcroft, Jared Casper, Jatin Mitra, Jeffrey Glick, Jenny Chen, Jesse Oliver, Jiacheng Xu, Jiafan Zhu, Jialin Song, Jian Zhang, Jiantao Jiao, Jiaqi Zeng, Jie Lou, Jim King, Jimmy Zhang, Jingquan Wang, Jinhang Choi, Jinju Chu, Joey Conway, Joey Guman, Johan Jatko, Johannes Rausch, John Kamalu, John Roberts, Johnny Greco, Johnny Mensel, Jonah Alben, Jonas Yang, Jonathan Cohen, Jonathan Raiman, Joseph Jennings, Joshua Mabry, Joshua Pierce, Joyjit Daw, Julien Veron Vialard, Junkeun Yi, Jupinder Parmar, Kajal Jain, Kan Zhu, Kari Briski, Katherine Cheung, Katherine Luna, Keith Willowhawk, Keith Wyss, Keshav Santhanam, Kevin Shih, Kezhi Kong, Khanh Nguyen, Khushi Bhardwaj, Kirthi Shankar Sivamani, Konstantinos Krommydas, Krishna C. Puvvada, Krzysztof Pawelec, Kumar Anik, Kyle Keprios, Kylie Day, Lawrence McAfee, Leo Du, Leon Derczynski, Li Ding, Linda Liu, Lingjie Wu, Lior Kadoch, Lizzie Wei, Luis Vega, Luke Robison, Lun Su, Maarten Van Segbroeck, Maciej Jakub Mikulski, Maer Rodrigues de Melo, Magda Sypula, Mahan Fathi, Makesh Narsimhan Sreedhar, Makesh Tarun Chandran, Manoj Kilaru, Maor Ashkenazi, Marc Cuevas, Marc Romeijn, Marcin Chochowski, Mark Cai, Mark Mozolewski, Markus Kliegl, Marta Stepniewska-Dziubinska, Martyna Patelka, Mattei Machczynski, Matvei Novikov, Mauricio Ferrato, Maximilian Golub, Mehrzad Samadi, Melissa Corpuz, Mengru Wang, Mengxi Wu, Meredith Price, Meriem Boubdir, Micah Schaffer, Michael Andersch, Michael Boone, Michael Gschwind, Michael Lightstone, Michael Loh, Michal Bien, Michal Zawalski, Michelle Gill, Miguel Martinez, Mikail Khona, Mike Chrzanowski, Mike Houston, Mingyuan Ma, Minseok Lee, Mohamed Fawzy, Mohammad Dabbah, Mohammad Shoeybi, Mostofa Patwary, Nabin Mulepati, Najeeb Nabwani, Namit Dhameja, Narimane Hennouni, Natalie Hereth, Nathaniel Pinckney, Nave Algarici, Nave Assaf, Netanel Haber, Nicholas Knight, Nick Reamaroon, Nickson Quak, Nidhi Bhatia, Nikhil Desai, Nikolai Ludwig, Nima Tajbakhsh, Ning Xu, Nir Ailon, Nirmal Juluru, Nitin Nitin, Ofri Masad, Oleg Rybakov, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivia Viessmann, Olivier Delalleau, Oluwatobi Olabiyi, Omer Ullman Argov, Omri Puny, Oren Tropp, Pablo Ribalta, Pallab Bhattacharya, Panos Lampropoulos, Parth Mannan, Pasha Shamis, Patrick Legresley, Paul Gibbons, Pavlo Molchanov, Pawel Morkisz, Peter Dykas, Peter Jin, Pierre-Yves Aquilanti, Pinky Xu, Piotr Januszewski, Piotr Laskiewicz, Pooya Jannaty, Prakash Gurumurthy, Pranav Prashant Thombre, Prasoon Varshney, Pritam Gundecha, Przemek Tredak, Puhui Meng, Qiyu Wan, Rabeeh Karimi Mahabadi, Rachel Oberman, Rachit Garg, Radha Sri-Tharan, Rahul Kandu, Rakshit Sanadhya, Ran El-Yaniv, Ran Zilberstein, Rasoul Shafipour, Ray Macalisang, Rayen Tian, Reka Kovacs, Renjie Pi, Rick Izzo, Rima Shahbazyan, Rishabh Garg, Rishi Puri, Rita Fernandes Neves, Ritchie Zhao, Ritika Borkar, Ritu Gala, Riyad Islam, Robert Clark, Robert Hesse, Robert Kirby, Roger Waleffe, Rohit Watve, Roi Koren, Ron Banner, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Ryan Stewart, Ryota Egashira, Sadegh Mahdavi, Saee Paliwal, Sagar Singh, Sahil Modi, Salika Dave, Samantha Shinagawa, Samuel Kriman, Sandip Bhaskar, Sangkug Lym, Sanjay Kariyappa, Sanjeev Satheesh, Saran Vikas Murari, Satish Pasumarthi, Saurabh Mishra, Saurav Muralidharan, Scott Hara, Sean Narentharen, Selvaraj Anandaraj, Seonjin Na, Seonmeyong Bak, Seonmyeong Bak, Sepehr Sameni, Seph Mard, Serge Panev, Seth Henneman, Seth Poulos, Shahar Mor, Shantanu Acharya, Shaona Ghosh, Sharath Turuvekere Sreenivas, Sharon Mendelson, Shaun Kotek, Shawn Wang, Shay Aharon, Shaya Gharghabi, Sheng-Chieh Lin, Shi Chen, Shiqing Fan, Shirish Baskaran, Shreya Gopa, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shuoyang Ding, Shwetha Krishnamurthy, Siddharth Singh, Simeng Sun, Sirshak Das, Sivakumar Arayandi Thottakara, Smita Ithape, Somshubra Majumdar, Soumye Singhal, Sri Harsha Singudasu, Sridhar Bhuvanapalli, Srimukh Veccham, Stas Sergienko, Stefania Alborghetti, Stephen Ge, Su Rong, Sugam Dipak Devare, Sukrit Rao, Sumeet Kumar Barua, Sungsoo Ha, Sunny Gai, Suriya Gunasekar, Suseella Panguluri, Suyog Gupta, Sviataslau Hinzburh, Sweta Priyadarshi, Syeda Nahida Akter, Talor Abramovich, Tan Bui, Tanay Varshney, Tatevik Ter-Hovhannisyan, Teodor-Dumitru Ene, Terry Kong, Thanh Do, Tianhe Zhang, Tiffany Moore, Tijmen Blankevoort, Tim Moon, Tiyasa Mitra, Tom Balough, Tomasz Grzegorzek, Tomasz Hliwiak, Tomer Asida, Tomer Bar Natan, Tomer Keren, Tomer Ronen, Tony Salim, Tony Wang, Traian Rebedea, Tugrul Konuk, Twinkle Vashishth, Udi Karpas, Ushnish De, Vahid Noorozi, Venkat Srinivasan, Venmugil Elango, Vibhor Agrawal, Victor Cui, Vijay Korthikanti, Vikas Mehta, Vinay Rao, Virginia Wu, Vitaly Kurin, Vitaly Lavrukhin, Vladimir Anisimov, Vu Pham, Wanli Jiang, Wasi Uddin Ahmad, Wataru Ishihara, Wei Du, Wei Ping, Weiheng Chai, Wenliang Dai, Wesley Helmholz, Will Jennings, Will Zhu, Wojciech Prazuch, Xiaowei Ren, Xiwen Yu, Yan Breek, Yang Chen, Yang Yu, Yangyi Chen, Yaniv Galron, Yashaswi Karnati, Yejin Choi, Yev Meyer, Yi-Fu Wu, Yian Zhang, Ying Lin, Yonatan Geifman, Yonggan Fu, Youngeun Kwon, Yu Yao, Yugi Guvvla, Yuki Huang, Yunsheng Liu, Zach Moshe, Zachary Newell, Zhilin Wang, Zhiyu Li, Zhongbo Zhu, Zhuolin Yang, Zihan Liu, Zijie Yan, Zsolt-Alon Wertheimer

机构 * NVIDIA（英伟达） 纠错

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

AI总结 提出550B总参数量、55B激活参数的混合专家Mamba-Attention语言模型Nemotron 3 Ultra，通过20T tokens预训练、1M上下文扩展及后训练，在推理吞吐量提升约6倍的同时保持与顶尖模型相当的精度。

Fact-Augmented Lookahead Planning for LLM Agents

面向LLM智能体的事实增强前瞻规划

Samuel Holt, Max Ruiz Luyten, Thomas Pouplin, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） 纠错

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

AI总结 提出LWM-Planner框架，通过从轨迹中提取关键事实并用于条件化动作提议、世界模型模拟和状态值估计，实现无需参数更新的在线规划改进，在多个环境上优于ReAct/Reflexion和纯搜索基线。

Comments Accepted at the 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026). Camera-ready version. 9-page main text plus appendices (63 pages total), 1 figure

Systems-Level Planning and Coordination of Truck-Drone Collaborative Delivery Networks

卡车-无人机协同配送网络的系统级规划与协调

Didem Cicek, Burak Kantarci

机构 * School of Electrical Engineering and Computer Science at the University of Ottawa（渥太华大学电气工程与计算机科学学院） 纠错

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

AI总结 针对城市最后一英里配送，提出分层规划与协调框架，通过任务编排与智能体同步，实现卡车-无人机协同配送，相比纯卡车模式，总配送时间减少42.4%，能耗降低44.2%。

Comments 6 pages, 4 figures, Accepted to 2026 IEEE HPSR on Network Architectures and Intelligence for Smart Mobility and Autonomous Systems (TRAVERSAL)

HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation

HARPO：面向用户对齐的对话推荐的分层代理推理

Subham Raj, Aman Vaibhav Jha, Mayank Anand, Sriparna Saha

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

AI总结 HARPO通过分层代理推理框架优化多维推荐质量，结合上下文依赖的偏好学习、 deliberative树搜索和领域无关的推理抽象，提升推荐质量与用户对齐性。

Comments Accepted at the Annual Meeting of the Association for Computational Linguistics (ACL 2026)

DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use

DexFuture: 用于双手灵巧工具使用的分层未来状态视觉运动目标

Runfa Blark Li, Kuang-Ting Tu, Nikola Raicevic, Dwait Bhatt, Xinshuang Liu, Keito Suzuki, Ki Myung Brian Lee, Nikolay Atanasov, Truong Nguyen

机构 * UC San Diego（圣迭戈大学） 纠错

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

AI总结 提出DexFuture分层系统，通过高层未来状态视觉运动目标预测器和低层目标条件结构化灵巧策略，实现双手灵巧工具使用，达到90%的特权oracle性能，运行速度60Hz，比DexWM式CEM规划快约250倍。

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

TRACE: 任务感知的自适应自我进化代理越狱

Churui Zeng, Weiwei Qi, Kedong Xiu, Tianhang Zheng, Chaochao Lu, Liang He, Zhan Qin, Kui Ren

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

AI总结 提出TRACE框架，通过任务分解、场景伪装和Q学习进化，实现LLM代理的高效越狱，在AgentHarm和AdvCUA上达到最高100%绕过率。

Comments 16 pages, 7 figures

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

LongDS-Bench：关于长周期智能数据分析的失败

Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding, Haoming Xu, Lei Liang, Ningyu Zhang

机构 * Zhejiang University（浙江大学） ； Ant Group（蚂蚁集团） ； Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph（知识图谱联合实验室） 纠错

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

AI总结 提出LongDS基准，用于评估长周期多轮数据分析中智能体维护和更新分析状态的能力，发现最佳模型平均准确率仅48.45%，且长周期错误占失败原因的52%-69%。

Comments Ongoing work

Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents

计划方式重要吗？LLM网络代理计划表示的实证研究

Alejandra Zambrano, Sara Vera Marjanovic, Imene Kerboua, Xing Han Lù, Leila Kosseim

机构 * Concordia University（康科德大学） ； Mila - Quebec AI Institute（魁北克人工智能研究所） ； University of Copenhagen（哥本哈根大学） ； Universite Claude Bernard Lyon（克莱尔蒙特-伯恩大学） ； McGill University（麦吉尔大学） 纠错

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

AI总结 本研究提出PlanAhead框架，通过自动难度分类和四种计划表示（顺序子目标、叙述、伪代码、检查清单）的对比实验，发现计划表示形式和生成计划的LLM显著影响网络代理的鲁棒性和任务成功率。

Comments Extended version of paper submitted to EMNLP, waiting for acceptance

EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

EpiAgent: 一种以智能体为中心的古铭文修复系统

Shipeng Zhu, Ang Chen, Na Nie, Pengfei Fang, Min-Ling Zhang, Hui Xue

机构 * School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其跨学科应用关键实验室（东南大学），教育部，中国） ； Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China（计算机网络与信息集成关键实验室（东南大学），教育部，中国） ； Nanjing University Museum, Nanjing University, China（南京大学博物馆，南京大学，中国） ； The China Centre for Linguistic and Strategic Studies, Nanjing University, China（中国语言战略研究中心，南京大学，中国） 纠错

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

AI总结 提出基于智能体的EpiAgent系统，通过分层规划与LLM协调多模态分析、历史经验和专用工具，实现灵活自适应的古铭文修复，在真实退化铭文上取得更优修复质量和泛化能力。

Comments Accepted by CVPR 2026

Sentinel: Embodied Cooperative Spatial Reasoning and Planning

Sentinel：具身协同空间推理与规划

Xiangye Lin, Hongxin Zhang, Ruxi Deng, Qinhong Zhou, Chuang Gan

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

AI总结 提出Sentinel挑战和CoSaR框架，通过自然语言通信与空间导航算法结合，解决多智能体在城市规模户外环境中的协同空间推理与规划问题。

Comments The first two authors contributed equally

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

智能体技能综述：分类、技术与应用

Yingli Zhou, Wang Shu, Yaodong Su, Wenchuan Du, Yixiang Fang, Xuemin Lin

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

AI总结 本文从智能体技能的生命周期（表示、获取、检索和演化）出发，系统综述了基于大语言模型的智能体在自动化复杂工作流中的技能定义、方法、资源及应用，并讨论了质量控制、互操作性、安全更新和长期能力管理等挑战。

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

从试错中学习：具身大语言模型的反思式测试时规划

Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Leonidas Guibas, Jiajun Wu, Yejin Choi

机构 * Stanford University（斯坦福大学） ； Northwestern University（西北大学） 纠错

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

AI总结 提出反思式测试时规划方法，通过行动中反思和行动后反思两种模式，结合回溯性反思，使具身智能体在测试时进行自我纠正和经验积累，显著提升长程任务性能。

Agent Learning via Early Experience

通过早期经验进行智能体学习

Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu

机构 * Meta Superintelligence Labs（Meta超智能实验室） ； FAIR at Meta（Meta的FAIR部门） ； The Ohio State University（俄亥俄州立大学） 纠错

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

AI总结 提出早期经验范式，利用智能体自身动作生成的交互数据（无需奖励信号）通过隐式世界建模和自我反思两种策略提升智能体在多样化环境中的效果和跨域泛化能力。

Comments ICML 2026

NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestration

NaviAgent: 一种基于图的双层规划用于可扩展的工具编排

Yan Jiang, Hao Zhou, Lizhong GU, Tianlong Li, Ruinan Jin, Wanqi Zhou, Ai Han

机构 * Department of Electrical and Computer Engineering, The Ohio State University, USA（电气与计算机工程系，俄亥俄州立大学，美国） 纠错

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

AI总结 本文提出NaviAgent，一种基于图的双层规划框架，通过解耦任务规划与工具执行，提升大规模工具编排的可扩展性和鲁棒性，实验表明其在任务成功率和实际应用中表现优异。

Comments Accepted to ICML 2026

Journal ref Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026

TopoClaw: A Human-Centric and Topology-Aware Agent Operating System

TopoClaw：一种以人为本且拓扑感知的代理操作系统

Heyuan Huang, Yeyi Guan, Jihong Wang, Mingzhi Wang, Jiamu Zhou, Xiangmou Qu, Jiaxin Yin, Xin Liao, Xingyu Lou, Jun Wang

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

AI总结 TopoClaw提出一种以人为本的拓扑感知代理操作系统，通过物理设备拓扑与社会关系拓扑的耦合结构，实现跨设备动作放置、跨用户身份归属和跨上下文权限治理，提升分布式协作与安全管控能力。

Accelerating Time-Optimal Trajectory Planning for Connected and Automated Vehicles with Graph Neural Networks

利用图神经网络加速连接和自动化车辆的时间最优轨迹规划

Viet-Anh Le, Andreas A. Malikopoulos

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

AI总结 本文提出基于学习的框架，利用图神经网络加速连接和自动化车辆的时间和能量最优轨迹规划，通过实时重规划提升性能，采用GINEConv网络学习离线数据以加速计算，减少计算时间并保持控制性能。

Comments final IFAC WC 2026