AI Agent

2509.20932 2025-09-26 cs.GT cs.LO cs.MA cs.SC 67%

A Category Theoretic Approach to Approximate Game Theory

Neil Ghani

专题命中多智能体：agent(abstract)；multi-agent(abstract)

Comments In Proceedings ACT 2024, arXiv:2509.18357

Journal ref EPTCS 429, 2025, pp. 190-202

2509.21017 2025-09-26 physics.soc-ph cs.MA 50%

Study on Locomotive Epidemic Dynamics in a Stochastic Spatio-Temporal Simulation Model on a Multiplex Network

H. M. Shadman Tabib, Jaber Ahmed Deedar, K. M. Ariful Kabir

专题命中多智能体：agent(abstract)

2509.20631 2025-09-26 cs.SE cs.LG 81%

Design, Implementation and Evaluation of a Novel Programming Language Topic Classification Workflow

Michael Zhang, Yuan Tian, Mariam Guizani

机构 * Queen's University（皇后大学）

专题命中工作流自动化：workflow(title,abstract)；分类 cs.LG、cs.SE

2110.02248 2025-09-26 cs.LG stat.AP stat.ML 57%

Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes

Andi Nika, Sepehr Elahi, Cem Tekin

机构 * Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）； Department of Computer and Communication Sciences（计算机与通信科学系）； Department of Electrical and Electronics Engineering（电气与电子工程系）

专题命中工作流自动化：agent(abstract)；分类 cs.LG

Comments 34 pages, 7 figures

2509.21132 2025-09-26 q-bio.QM stat.AP 50%

Detecting disease progression from animal movement using hidden Markov models

Dongmin Kim, Théo Michelot, Katherine Mertes, Jared A. Stabach, John Fieberg

专题命中工作流自动化：workflow(abstract)

2509.20469 2025-09-26 astro-ph.IM astro-ph.EP 50%

Technical Memo: The impact of Nancy Grace Roman Telescope's default image processing on the detectability of moving Solar system objects

Joseph Masiero

专题命中工作流自动化：planning(abstract)

Comments Technical Memo, 7 pages

2509.12408 2025-09-26 cs.HC 50%

Scaffolding Flexible Ideation Workflows with AI in Creative Problem-Solving

Yaqing Yang, Vikram Mohanty, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew K. Hong

专题命中工作流自动化：workflow(abstract)

Comments Accepted as a poster to ACM Collective Intelligence 2025

2407.07709 2025-09-26 physics.med-ph 50%

Motion simulation of radio-labeled cells in whole-body positron emission tomography

Nils Marquardt, Tobias Hengsbach, Marco Mauritz, Benedikt Wirth, Klaus Schäfers

专题命中工作流自动化：workflow(abstract)

Comments 12 pages, 12 figures

2410.12010 2025-09-26 cs.LG cs.AI cs.CL 67%

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs

Hyejun Jeong, Shiqing Ma, Amir Houmansadr

机构 * UMass Amherst（马萨诸塞大学阿姆赫斯特分校）

专题命中软件智能体：workflow(abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Code available at https://github.com/HyejunJeong/bias_llm

2506.03136 2025-09-26 cs.CL 57%

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

Yinjie Wang, Ling Yang, Ye Tian, Ke Shen, Mengdi Wang

机构 * University of Chicago（芝加哥大学）； Princeton University（普林斯顿大学）； Peking University（北京大学）； ByteDance Seed（字节跳动种子）

专题命中软件智能体：agentic(abstract)；分类 cs.CL

Comments NeurIPS 2025 Spotlight. Project: https://github.com/Gen-Verse/CURE

2509.21189 2025-09-26 cs.RO cs.AI cs.CV 57%

Human-like Navigation in a World Built for Humans

Bhargav Chandaka, Gloria X. Wang, Haozhe Chen, Henry Che, Albert J. Zhai, Shenlong Wang

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

专题命中 GUI与网页智能体：agent(abstract)；分类 cs.AI

Comments CoRL 2025. Project website: https://reasonnav.github.io/

2411.13987 2025-09-26 eess.SP 50%

Universal Scanning GUI Tool for Available and Usable TV White Space (TVWS) Spectrum

Muneer Al-ZuBi, Mohamed-Slim Alouini

专题命中 GUI与网页智能体：planning(abstract)

2509.21301 2025-09-26 cs.OS 82%

Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization

Yuhang Xu, Shengzhong Liu, Dong Zhang, Bingheng Yan, Fan Wu, Guihai Chen

专题命中记忆与上下文管理：agentic(title,abstract)；agent(abstract)

2509.20600 2025-09-26 cs.NI cs.AI cs.LG 81%

An LLM-based Agentic Framework for Accessible Network Control

Samuel Lin, Jiawei Zhou, Minlan Yu

机构 * Meta ； Stony Brook University（石溪大学）； Harvard University（哈佛大学）

专题命中记忆与上下文管理：agentic(title,abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 6 figures

Journal ref AI Crossroads: Systems, Energy, and Applications Workshop of ACM SIGMETRICS 2025 Conference

2508.04495 2025-09-26 cs.LG cs.CL 62%

Causal Reflection with Language Models

Abi Aryan, Zac Liu

机构 * Abide AI

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL、cs.LG

2509.21224 2025-09-26 cs.AI 57%

What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns

Stefan Szeider

机构 * Algorithms and Complexity Group TU Wien（算法与复杂性组维也纳技术大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2509.21129 2025-09-26 cs.LG cs.CR 57%

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense

Wei Huang, De-Tian Chu, Lin-Yuan Bai, Wei Kang, Hai-Tao Zhang, Bo Li, Zhi-Mo Han, Jing Ge, Hai-Feng Lin

机构 * People’s Liberation Army 77606 Unit（中国人民解放军77606单位）； Field Engineering College, Army Engineering University of PLA（陆军工程大学工程学院）； College Of Software, ZhengZhou University of Light Industry（郑州轻工业大学软件学院）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2509.20754 2025-09-26 cs.AI cs.RO 57%

Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial Reasoning

Yufan Mao, Hanjing Ye, Wenlong Dong, Chengjie Zhang, Hong Zhang

机构 * Southern University of Science and Technology（南方科技大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2503.09447 2025-09-26 cs.AI cs.CV cs.RO 57%

Online Language Splatting

Saimouli Katragadda, Cho-Ying Wu, Yuliang Guo, Xinyu Huang, Guoquan Huang, Liu Ren

机构 * University of Delaware（德克萨斯大学）； Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI)（博世北美研究部及博世人工智能中心（BCAI））

专题命中记忆与上下文管理：AI agent(abstract)；分类 cs.AI

2412.18907 2025-09-26 cs.AI cs.CV cs.RO 57%

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

Carl Qi, Dan Haramati, Tal Daniel, Aviv Tamar, Amy Zhang

机构 * UT Austin（得克萨斯大学）； Technion, Israel Institute of Technology（技术学院，以色列技术学院）； Brown University（布朗大学）； Meta AI

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2509.20731 2025-09-26 cs.HC cs.AI 85%

Imagining Design Workflows in Agentic AI Futures

Samangi Wadinambiarachchi, Jenny Waycott, Yvonne Rogers, Greg Wadley

机构 * The University of Melbourne（墨尔本大学）； University College London（伦敦大学学院）

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

Comments 37th Australian Conference on Human-Computer Interaction (HCI) (OZCHI '25)

2509.20998 2025-09-26 cs.AI 81%

CORE: Full-Path Evaluation of LLM Agents Beyond Final State

Panagiotis Michelakis, Yiannis Hadjiyiannis, Dimitrios Stamoulis

机构 * Synkrasis Labs（Synkrasis实验室）； Harbin Institute of Technology（哈尔滨工业大学）

专题命中 Agent评测：agent(abstract)；AI agent(abstract)；tool-use(abstract)；agentic(abstract)

Comments Accepted: LAW 2025 Workshop NeurIPS 2025

2509.21291 2025-09-26 cs.AI cs.CV 79%

VC-Agent: An Interactive Agent for Customized Video Dataset Collection

Yidan Zhang, Mutian Xu, Yiming Hao, Kun Zhou, Jiahao Chang, Xiaoqiang Liu, Pengfei Wan, Hongbo Fu, Xiaoguang Han

机构 * SSE, The Chinese University of Hong Kong, Shenzhen（深圳中文大学香港科技大学 SSE）； The Hong Kong University of Science（香港科学大学）

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

Comments Project page: https://allenyidan.github.io/vcagent_page/

2509.20538 2025-09-26 q-bio.PE nlin.PS 71%

Pattern Formation in Agent-Based and PDE Models for Evolutionary Games with Payoff-Driven Motion

Tianyong Yao, Chenning Xu, Daniel B. Cooney

专题命中 Agent评测：agent(title)

Comments 56 pages, 15 figures, equal contribution from TY and CX

2509.17350 2025-09-26 cs.RO 67%

DyDexHandover: Human-like Bimanual Dynamic Dexterous Handover using RGB-only Perception

Haoran Zhou, Yangwei You, Shuaijun Wang

机构 * Xiaomi Robotics（小米机器人）

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

Comments 8 pages, 7 figures

2509.21126 2025-09-26 cs.LG cs.AI 62%

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning

Xiefeng Wu, Jing Zhao, Shu Zhang, Mingyu Hu

机构 * Wuhan University（武汉大学）

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

2509.21234 2025-09-26 cs.LG cs.MA 57%

AbideGym: Turning Static RL Worlds into Adaptive Challenges

Abi Aryan, Zac Liu, Aaron Childress

机构 * Abide AI

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2509.21188 2025-09-26 cs.HC cs.AI cs.CY cs.IR 57%

Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey

Kolawole Tytler

专题命中 Agent评测：workflow(abstract)；分类 cs.AI

2404.02688 2025-09-26 cs.LG math.CT 57%

Reinforcement Learning in Categorical Cybernetics

Jules Hedges, Riu Rodríguez Sakamoto

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments In Proceedings ACT 2024, arXiv:2509.18357

Journal ref EPTCS 429, 2025, pp. 270-286

2312.12260 2025-09-26 math.CO cs.GT 50%

Connectedness in weighted consensus division of graphical cakes between two agents

Josef Hanke, Ana Rita Pires

专题命中 Agent评测：agent(abstract)

Comments This version agrees with the published version. 11 pages, 4 figures

Journal ref Mathematical Social Sciences Mathematical Social Sciences, Volume 138, December 2025, 102463

1. 多智能体 8 篇

A Category Theoretic Approach to Approximate Game Theory

Study on Locomotive Epidemic Dynamics in a Stochastic Spatio-Temporal Simulation Model on a Multiplex Network

2. 工作流自动化 6 篇

Design, Implementation and Evaluation of a Novel Programming Language Topic Classification Workflow

Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes

Detecting disease progression from animal movement using hidden Markov models

Technical Memo: The impact of Nancy Grace Roman Telescope's default image processing on the detectability of moving Solar system objects

Scaffolding Flexible Ideation Workflows with AI in Creative Problem-Solving

Motion simulation of radio-labeled cells in whole-body positron emission tomography

3. 软件智能体 2 篇

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

4. GUI与网页智能体 2 篇

Human-like Navigation in a World Built for Humans

Universal Scanning GUI Tool for Available and Usable TV White Space (TVWS) Spectrum

5. 记忆与上下文管理 8 篇

Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization

An LLM-based Agentic Framework for Accessible Network Control

Causal Reflection with Language Models

What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense

Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial Reasoning

Online Language Splatting

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

6. Agent评测 10 篇

Imagining Design Workflows in Agentic AI Futures

CORE: Full-Path Evaluation of LLM Agents Beyond Final State

VC-Agent: An Interactive Agent for Customized Video Dataset Collection

Pattern Formation in Agent-Based and PDE Models for Evolutionary Games with Payoff-Driven Motion

DyDexHandover: Human-like Bimanual Dynamic Dexterous Handover using RGB-only Perception

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning

AbideGym: Turning Static RL Worlds into Adaptive Challenges

Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey

Reinforcement Learning in Categorical Cybernetics

Connectedness in weighted consensus division of graphical cakes between two agents