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 6372 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 规划决策 1830 篇

2606.15007 2026-06-16 cs.CL cs.AI cs.LG 新提交 85%

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)

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。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08738 2026-06-09 cs.NI cs.RO 新提交 85%

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)

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.13612 2026-08-17 cs.AI cs.SE 新提交 84%

SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data

SemPlan:面向企业数据的基于大语言模型(LLM)查询的结构化语义规划基准测试

Bruno Santos Teixeira

机构 * Universidade Federal de Ouro Preto (UFOP)(欧鲁普雷图联邦大学(UFOP))

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

AI总结 该研究构建了SemPlan基准测试,对比四种架构在企业数据LLM查询语义规划中的表现,发现结构化语义规划架构(A3)正确率最高,不同架构在正确率、策略合规性、成本等方面存在权衡。

Comments 11 pages, 3 figures, 9 tables. Submitted to Transactions on Machine Learning Research (TMLR)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.13581 2026-08-17 cs.HC cs.AI cs.LG 新提交 84%

From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent

从预测到干预:基于大语言模型智能体的个性化餐级血糖调节

Mingyu Huang, Weiqing Min, Ying Jin, Yilin Wang, Shuqiang Jiang

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

AI总结 针对精准营养中个性化血糖调节的挑战,提出融合生理学习与LLM智能体的系统,通过生理感知预测器和预测驱动优化智能体提升血糖预测准确率并降低血糖波动。

Comments Accepted in ACL 2026 Findings, 17 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.13571 2026-08-17 cs.CL cs.AI 新提交 84%

Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

并非所有token都平等:面向智能体大语言模型系统的感知通胀路由

Heming Fu, Shan Lin, Qianqian Xie, Guojun Xiong

机构 * Stony Brook University(石溪大学) Wuhan University(武汉大学) Shanghai Jiao Tong University(上海交通大学)

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

AI总结 针对智能体LLM系统的token通胀问题,提出四阶段路由框架InflationAgent,通过测量通胀、引入CBE信号、最大化SER并采用新鲜升级策略,在GSM8K上优于FrugalGPT。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.13560 2026-08-14 cs.CV cs.AI cs.CL 新提交 84%

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

AutoDesign:面向长视距智能体设计的元工具优化

Yaxin Luo, Haobin Jiang, Jialv Zou, Xu Huang, Wenhao Yan, Haodong Li, Zhengrong Yue, Jing Li, Xiaofu Chen, Xiaohan Zhao, Jiacheng Liu, Jiacheng Cui, Zhiqiang Shen, Xiaotong Li

机构 * Meituan(美团) MBZUAI(Mohamed bin Zayed University of Artificial Intelligence) Huazhong University of Science and Technology(华中科技大学) Peking University(北京大学) Tsinghua University(清华大学) The Chinese University of Hong Kong(香港中文大学) Shanghai Jiao Tong University(上海交通大学)

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

AI总结 AutoDesign是符合人类设计先验的元工具优化框架,以论文转海报生成任务为实例,在PosterBench上性能优于Claude Design,集成其学习的DesignHarness可提升代码智能体性能,且获人类最高偏好。

Comments Tech Report. Code at: https://github.com/Yaxin9Luo/AutoDesign

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10628 2026-08-12 cs.CV cs.CL cs.LG 新提交 84%

InSight-doc: Agentic Visual Perception for Long-Document Understanding

InSight-doc:面向长文档理解的智能体视觉感知框架

Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang, Nevin L. Zhang

机构 * The Hong Kong University of Science and Technology(香港科技大学) Huawei(华为)

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

AI总结 本研究提出智能体视觉感知框架InSight-doc,通过自适应选择放大高分辨率区域处理长文档,经SFT+RL训练后在文档VQA任务中显著提升准确率、降低幻觉与推理延迟,相关资源已公开。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.06961 2026-08-10 cs.AI cs.LG 新提交 84%

CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows

CAi Copilot:通过意图驱动的智能体工作流减少分子设计中的操作工作量

Zhu Wang, Jiangyu Chen, Yingjun Shang, Yuhui Yao, Laiao Lu, Tianfan Fu, Na Zou

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Nanjing University(南京大学)

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

AI总结 CAi Copilot是面向专家的意图驱动智能体,通过三层架构整合分子设计分散工具,在45项任务中整体性能最优,得分84.59,可将设计意图转化为可追溯工作流。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.05499 2026-08-07 cs.CV cs.AI cs.LG 新提交 84%

APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

APQF:基于智能体分析引导的结构化剪枝与混合精度量化及自适应微调

Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou, Brian Gelder, Ali Jannesari

机构 * Iowa State University(爱荷华州立大学)

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

AI总结 APQF是结合LLM引导与分析支撑的自动化剪枝量化框架,在ImageNet等数据集上实现高压缩比且精度接近基线,优于现有联合剪枝量化方法。

Comments 22 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.04588 2026-08-06 cs.CL cs.AI 新提交 84%

EASy: Towards Efficient LLM-Based Agentic System

EASy:迈向高效的基于大语言模型的智能体系统

Junnan Liu, Linhao Luo, Thuy-Trang Vu, Gholamreza Haffari

机构 * Monash University(莫纳什大学)

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

AI总结 EASy是一种可训练的智能体框架,通过强化学习优化任务性能与计算效率,采用里程碑-规划-执行工作流,在多类基准上实现了更优的性能-效率权衡。

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00339 2026-08-04 cs.AI cs.CL 新提交 84%

Bayesian and Motivated Reasoning in AI Agents

AI智能体中的贝叶斯推理与动机推理

Eddie Yang

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

AI总结 该研究发现AI智能体的结论受先验信念影响,相同数值数据因框架不同会得出不同结论,揭示了委托其决策存在依赖未指定先验的风险。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.25090 2026-07-29 cs.AI cs.LG 新提交 84%

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering

套娃智能体:展开子智能体以进行长期机器学习工程

Rushi Qiang, Changhao Li, Haotian Sun, Yuchen Zhuang, Chao Zhang, Bo Dai

机构 * Georgia Institute of Technology(佐治亚理工学院)

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

AI总结 针对机器学习工程长期决策难题,提出套娃智能体框架,将问题解决分解为协调层次结构,高级协调器发指令,低级子智能体执行,开发有效训练范式,实验证明该方法有效且可扩展,能提升性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22385 2026-07-27 cs.AI cs.LG 新提交 84%

Agentic Root Cause Analysis through Evidence-Grounded Reasoning

通过基于证据的推理进行智能根本原因分析

Amaury Wei, Olga Fink

机构 * EPFL - IMOS Laboratory(洛桑联邦理工学院 - IMOS实验室)

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

AI总结 研究针对工业异常根本原因诊断依赖人工且现有数据驱动方法有局限的问题,提出AgentRCA框架,结合数字孪生和大语言模型进行推理,在实际设施上评估,性能与监督基线相当且能产生透明推理轨迹,为工业根本原因分析提供实用基础。

Comments 21 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.21653 2026-07-27 cs.LG cs.CL cs.DC 新提交 84%

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Molt:用于智能体强化学习的可扩展原生 PyTorch 训练框架

Jian Hu, Huiying Li, Hao Zhang, Binfeng Xu, Yifan Zhang, Shaokun Zhang, Hemil Desai, Michael Demoret, Pavlo Molchanov, Jan Kautz, Yi Dong

机构 * NVIDIA(英伟达)

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

AI总结 研究针对智能体强化学习中算法修改成本高的问题,提出原生 PyTorch 训练框架 Molt,其代码简洁,智能体是普通程序,通过异步循环训练策略,在全异步协议下性能与先进堆栈相当,且开源提供资源。

Comments tech report for Molt

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.19913 2026-07-23 cs.AI cs.CL cs.CR 新提交 84%

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety

JANUS:预见长期智能体安全中的潜在风险

Yuan Xiong, Linji Hao, Shizhu He, Yequan Wang, Lijun Li

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

AI总结 研究长期智能体安全潜在风险,提出JANUS框架,通过多智能体模拟合成轨迹,经预测与裁决耦合任务学习共享策略,用CoAA-RL联合优化,所产生的Vanguard模型提升了智能体安全防护及任务完成率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.18806 2026-07-22 cs.AI cs.CL cs.MA 新提交 84%

AI Tour Meeting: Group Travel Planning by LLM Agents

人工智能旅游会议:基于大语言模型代理的团体旅行规划

Daisuke Kikuta

机构 * NTT, Inc.(日本电报电话公司)

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

AI总结 提出基于大语言模型代理的团体旅行规划框架AI Tour Meeting,通过自然语言讨论找满足约束和偏好的行程,提供相关配置接口实现灵活编排,可作模拟工具,还展示了系统验证等结果以证明其效用。

Comments The code is available at https://github.com/ntt-dkiku/ai-tour-meeting

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.18589 2026-07-22 cs.LG cs.AI 新提交 84%

Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States

关系隐藏状态强化学习中作为涌现行为的规划

Armin Sommer

机构 * ETH Zurich(苏黎世联邦理工学院)

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

AI总结 研究无模型强化学习中规划作为涌现行为的现象,发现神经架构的隐藏状态结构是决定因素,关系隐藏状态网络能获规划机制,恢复环境转移结构并改进策略,解释了涌现规划现象并引发相关问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.17780 2026-07-21 cs.PL cs.AI cs.LG cs.MA 新提交 84%

ETAS: An Effect-Typed Language for Agent Systems

ETAS:一种用于智能体系统的效果类型化语言

Huiri Tan, Yikun Wang, Puyang Zhang, Shangyu Li, Jiasi Shen

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

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

AI总结 研究针对智能体系统设计ETAS语言,核心方法是通过规范一致性分配类型并用行为索引跟踪计算,主要贡献是为智能体执行相关推理提供编程语言基础,涵盖授权、非确定性等方面,还实现了该语言并形式化相关性质。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.17225 2026-07-21 cs.SE cs.AI 新提交 84%

Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI

指定委托自治边界:智能体人工智能的需求工程

Chetan Arora, Andreas Vogelsang, Abbi Sharma

机构 * Faculty of IT, Monash University(莫纳什大学信息科技学院) University of Duisburg-Essen(杜伊斯堡-埃森大学)

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

AI总结 研究智能体人工智能系统带来的需求工程问题,提出机构理由记录和智能体委托策略两个互补工件,通过分级建模权限,以医院出院协调智能体和自动代码审查智能体为例阐释框架,解决委托自治边界相关需求工程问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.14642 2026-07-17 cs.AI cs.SE 新提交 84%

MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers

MCPEvol-Bench:跨MCP服务器动态演化对大语言模型智能体性能进行基准测试

Huanxi Liu, Kun Hu, Jiaqi Liao, Qiang Wang, Pengfei Qian, YuanZhao Zhai, Dawei Feng, Bo Ding, Huaimin Wang

机构 * College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院) State Key Laboratory of Complex & Critical Software Environment(复杂关键软件环境国家重点实验室) National Key Laboratory of Parallel and Distributed Computing(并行与分布式计算国家重点实验室)

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

AI总结 研究针对MCP服务器工具接口和功能持续演化致评估有缺陷的问题,引入MCPEvol-Bench基准测试,提出11种变异算子模拟工具演化,对12个先进大语言模型测试,发现前沿模型也难适应,凸显大语言模型驱动工作流程脆弱性,确立评估标准。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.09175 2026-07-13 cs.AI cs.CL 新提交 84%

Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift

分布转移下可靠长时代理上下文演化的范围验证

Dan C. Hsu, Luke Lu

机构 * RedMind Research(红芯研究公司) National Taiwan University(国立台湾大学)

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

AI总结 研究长时代理上下文演化在分布转移下的验证问题,提出图正则化代理上下文演化方法(GRACE),通过维护指令为类型化语义图并在局部验证更新,实验表明该方法显著提升了严格可靠性。

Comments 18 pages, 3 figs

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.07178 2026-07-09 cs.LG cs.AI 新提交 84%

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

多任务智能强化学习的熵步长策略优化

Zetian Hu, Shunyu Liu, Junjie Zhang, Yongcheng Jing, Ting-En Lin, Yongbin Li, Dacheng Tao

机构 * Generative AI Lab, College of Computing and Data Science, Nanyang Technological University(生成式人工智能实验室,南洋理工大学计算与数据科学学院) Tongyi Lab, Alibaba Group(阿里集团通义实验室)

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

AI总结 研究多任务智能强化学习中任务间探索-利用步长不匹配问题,提出熵步长策略优化(EPPO),核心是任务级动态裁剪机制,实验证明EPPO在多任务智能基准上结果优于同类方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.05804 2026-07-08 cs.AI cs.CL 新提交 84%

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

TurnOPD:使在线策略蒸馏具有转向意识以实现高效的长期智能体训练

Yuhang Zhou, Kai Zheng, Haoling Li, Dengyun Peng, Can Xu, Jingjing Chen

机构 * Fudan University(复旦大学) Tencent Hunyuan(腾讯文言)

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

AI总结 研究针对在线策略蒸馏在长期智能体任务应用不足的问题,提出TurnOPD,通过自适应展开深度预算和渐进式转向归一化损失预算两个策略,在多任务实验中实现更高验证准确率,超越普通OPD,推进了准确率-时间前沿。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.05001 2026-07-08 cs.CR cs.AI cs.LG cs.MA 新提交 84%

TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction

TACTIC-KG:面向网络威胁情报知识图谱构建的小型智能体团队

Mouhamed Amine Bouchiha, Gregory Blanc

机构 * SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris(SAMOVAR, Telecom SudParis, Institute of Paris Polytechnic)

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

AI总结 研究针对网络威胁情报报告构建知识图谱的问题,提出TACTIC-KG框架,将任务分解给模块化专业语言模型智能体,用轻量级模型提升性能并降低成本,实验表明优于整体式模型。

Comments 20 pages, 2 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.02588 2026-07-07 cs.CV cs.AI cs.CL 新提交 84%

Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning

荷马:通过分层记忆和智能推理理解长视频

Yixin Ji, Fanghua Ye, Juntao Li, Bo Zhao, Zexuan Qiu, Zhaopeng Tu, Liefeng Bo, Min Zhang

机构 * Soochow University(苏州大学) Tencent Hunyuan Multimodal Department(腾讯混元多模态部)

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

AI总结 研究长视频理解问题,提出荷马分层在线记忆探索与推理框架,其记忆反映视频多尺度结构,智能推理器按人类方式探索记忆,通过多轮检索组合答案,性能优于此前最佳方法。

Comments under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.02436 2026-07-03 cs.SE cs.AI 新提交 84%

Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

推理努力,而非工具访问,决定了智能体代码生成的首试可靠性:一项观察性研究

Achint Mehta

机构 * TrendAI

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

AI总结 本研究通过90次独立智能体运行构建同一应用,发现推理努力(从高到极高)将首试完美运行率从28%提升至89%,而测试工具虽增加成本却未改善功能得分或可靠性。

Comments 22 pages, 5 figures, 10 tables. Dataset and evaluation artifacts: https://doi.org/10.5281/zenodo.21134406

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.30801 2026-07-01 cs.CL cs.CY cs.LG cs.SI 新提交 84%

Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale

使用AI代理自动化大规模黑盒审计个性化算法

Alessandro Morosini, Sarah H. Cen, Andrew Ilyas, Hedi Driss, Aleksander Mądry, Chara Podimata

机构 * Massachusetts Institute of Technology(麻省理工学院) Carnegie Mellon University(卡内基梅隆大学)

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

AI总结 提出用生成式AI代理作为行为引擎进行黑盒审计,通过固定人设和反事实扰动解耦用户属性与行为,在X平台部署1120个代理发现算法推荐放大有毒、极化内容且效果因用户意识形态而异。

Comments 43 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.14027 2026-07-01 cs.CR cs.AI cs.CL cs.SY eess.SY 新提交 84%

Same-Origin Policy for Agentic Browsers

代理浏览器的同源策略

Xilong Wang, Xiaoxing Chen, Patrick Li, Dawn Song, Neil Gong

机构 * Duke University(杜克大学) Stanford University(斯坦福大学) UC Berkeley(加州大学伯克利分校)

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

AI总结 研究代理浏览器中同源策略的有效性,构建SOPBench评估基准,发现现有代理浏览器频繁违反SOP,并提出SOPGuard机制来强制执行SOP,同时保持效用和低开销。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20641 2026-06-23 cs.RO cs.AI cs.LG 新提交 84%

MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning

MAGNIFIED: 多模态大语言模型的强化学习微调用于运动规划

Letian Chen, Yiren Lu, Justin Fu, Yichen Xie, Runsheng Xu, Jyh-Jing Hwang, Ben Sapp, Drago Anguelov

机构 * Waymo LLC(Waymo有限责任公司)

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

AI总结 提出MAGNIFIED方法,通过强化学习微调多模态大语言模型,利用令牌级奖励优化规划目标,在Waymo数据集上显著降低重叠率和偏离道路率。

Journal ref ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20627 2026-06-23 cs.AI cs.LG 新提交 84%

Latent Goal Prediction from Language for Model-Based Planning

基于语言隐式目标预测的模型规划

Samuel Barbeau, Simon Roy, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome

机构 * École de Technologie Supérieure, Montréal(蒙特利尔高等技术学院) International Laboratory on Learning Systems (ILLS)(国际学习系统实验室) Polytechnique Montréal(蒙特利尔综合理工学院) MILA Institut Universitaire de France (IUF)(法国大学研究院) Université Sorbonne, CNRS, ISIR(索邦大学,法国国家科学研究中心,智能系统与机器人研究所)

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

AI总结 提出LAGO框架,通过在同一隐空间预测语言指令的中间子目标序列和动作条件轨迹,结合软最小轨迹代价规划,实现长程鲁棒规划。

Comments 9 pages. Preprint under review

详情

展开后加载摘要…

URL PDF HTML 收藏