AI Agent

2510.15556 2025-10-20 cs.CV 50%

Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics

Yitong Li, Ralph Buchert, Benita Schmitz-Koep, Timo Grimmer, Björn Ommer, Dennis M. Hedderich, Igor Yakushev, Christian Wachinger

机构 * Lab for AI in Medical Imaging, Institute for Diagnostic and Interventional Radiology, School of Medicine and Health（人工智能在医学影像中的实验室，诊断与介入放射学研究所，医学院与健康学院）； Technical University of Munich (TUM)（慕尼黑技术大学）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； University Medical Center Hamburg-Eppendorf（汉堡-埃本达大学医学中心）； Department of Neuroradiology, TUM University Hospital, School of Medicine and Health（神经放射学部，慕尼黑技术大学医院，医学院与健康学院）； Department of Neurology, TUM University Hospital, School of Medicine and Health（神经病学部，慕尼黑技术大学医院，医学院与健康学院）

专题命中工作流自动化：workflow(abstract)

2510.15490 2025-10-20 cs.DC 50%

Retrofitting Service Dependency Discovery in Distributed Systems

Diogo Landau, Gijs Blanken, Jorge Barbosa, Nishant Saurabh

专题命中工作流自动化：agent(abstract)

2510.15355 2025-10-20 cs.DC 50%

Cloud-Enabled Virtual Prototypes

Tim Kraus, Axel Sauer, Ingo Feldner

专题命中工作流自动化：workflow(abstract)

Comments 8 pages, 5 figures, Published in DVCon Europe 2025

2510.15237 2025-10-20 cs.PF 50%

Impact of AI-Triage on Radiologist Report Turnaround Time: Real-World Time-Savings and Insights from Model Predictions

Yee Lam Elim Thompson, Jonathan Fergus, Jonathan Chung, Jana G. Delfino, Weijie Chen, Gary M. Levine, Frank W. Samuelson

专题命中工作流自动化：workflow(abstract)

2505.22981 2025-10-20 cs.HC 50%

Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies

Siyang Liu, Sahand Sabour, Xiaoyang Wang, Rada Mihalcea

专题命中工作流自动化：agent(abstract)

2502.19396 2025-10-20 cond-mat.mtrl-sci 50%

How to choose efficiently the size of the Bethe-Salpeter Equation Hamiltonian for accurate exciton calculations on supercells

Rafael R. Del Grande, David A. Strubbe

专题命中工作流自动化：workflow(abstract)

Journal ref Phys. Rev. B 112, 165118 (2025)

2510.15128 2025-10-20 cs.AI cs.LG 62%

Towards Error Centric Intelligence I, Beyond Observational Learning

Marcus A. Thomas

机构 * Memorial Sloan Kettering（纪念斯隆凯特林医院）

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

2510.13432 2025-10-20 cs.CV 67%

CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation

Yushan Han, Hui Zhang, Honglei Zhang, Chuntao Ding, Yuanzhouhan Cao, Yidong Li

机构 * Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education and School of Computer Science and Technology, Beijing Jiaotong University（大数据与人工智能交通实验室（北京交通大学）及计算机科学与技术学院，北京交通大学）

专题命中 GUI与网页智能体：agent(abstract)；multi-agent(abstract)

Comments Accepted by IEEE Transactions on Mobile Computing

2505.11717 2025-10-20 cs.LG cs.AI cs.CL cs.CV 67%

WebInject: Prompt Injection Attack to Web Agents

Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, Neil Zhenqiang Gong

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

Comments Appeared in EMNLP 2025 main conference. To better understand prompt injection attacks, see https://people.duke.edu/~zg70/code/PromptInjection.pdf

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

2510.15455 2025-10-20 cs.CL 57%

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

Gucongcong Fan, Chaoyue Niu, Chengfei Lyu, Fan Wu, Guihai Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； Alibaba Group（阿里巴巴集团）

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

2507.07299 2025-10-20 cs.RO cs.CV 50%

MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation

Sonia Raychaudhuri, Enrico Cancelli, Tommaso Campari, Lamberto Ballan, Manolis Savva, Angel X. Chang

机构 * Simon Fraser University（西蒙弗雷泽大学）； University of Padova（帕多瓦大学）； Fondazione Bruno Kessler (FBK)（布鲁诺·克塞勒基金会）； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔人工智能研究所）

专题命中 GUI与网页智能体：agent(abstract)

2510.15261 2025-10-20 cs.AI 79%

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

Jitesh Jain, Shubham Maheshwari, Ning Yu, Wen-mei Hwu, Humphrey Shi

机构 * Adobe（Adobe公司）； Netflix Eyeline Studios（Netflix Eyeline工作室）； UIUC（伊利诺伊大学香槟分校）

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

Comments LAW 2025 Workshop at NeurIPS 2025. Work done from late 2023 to early 2024

2510.15772 2025-10-20 cs.AI 57%

Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL

Richard M. Bailey

机构 * University of Oxford（牛津大学）

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

Comments 50 pages, 4 figures

2510.15006 2025-10-20 cs.LG 57%

ES-C51: Expected Sarsa Based C51 Distributional Reinforcement Learning Algorithm

Rijul Tandon, Peter Vamplew, Cameron Foale

机构 * UIET, Panjab University , Chandigarh , India（旁遮普大学UIET，昌迪加尔，印度）； Federation University, Victoria, Australia（联邦大学，维多利亚，澳大利亚）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2510.15656 2025-10-20 nlin.AO cond-mat.stat-mech 50%

Active matter synchronization and synergetics

Frank Schweitzer, Georges Andres, Adrien Baut, Giona Casiraghi, Christoph Gote, Ramona Roller

专题命中记忆与上下文管理：agent(abstract)

2510.15186 2025-10-20 cs.CR cs.CL 88%

MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation

Gurusha Juneja, Jayanth Naga Sai Pasupulati, Alon Albalak, Wenyue Hua, William Yang Wang

机构 * University of California, Santa Barbara（加州大学圣芭芭拉分校）； University of California, Davis（加州大学戴维斯分校）

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

2503.23886 2025-10-20 cs.DB cs.AI 77%

Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language

Qin Wang, Youhuan Li, Yansong Feng, Si Chen, Ziming Li, Pan Zhang, Zihui Si, Yixuan Chen, Zhichao Shi, Zebin Huang, Guo Chen, Wenqiang Jin

机构 * Hunan University（湖南大学）； Peking University（北京大学）

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

Comments 19 pages, 16 figures

2510.04229 2025-10-20 cs.HC cs.AI 72%

When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue

Rikuo Sasaki, Michimasa Inaba

机构 * The University of Electro-Communications（电子通信大学）

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

Comments 23 pages, 19 figures. International Conference on Human-Agent Interaction (HAI 2025), November 10-13, 2025, Yokohama, Japan

2510.14049 2025-10-20 cs.LG cs.MS 70%

CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations

Guangyi Chen, Yunlong Deng, Peiyuan Zhu, Yan Li, Yifan Shen, Zijian Li, Kun Zhang

机构 * Carnegie Mellon University（卡内基梅隆大学）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

专题命中 Agent评测：agent(abstract)；multi-agent(abstract)；分类 cs.LG

2509.26490 2025-10-20 cs.CL cs.AI 62%

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Wei He, Yueqing Sun, Hongyan Hao, Xueyuan Hao, Zhikang Xia, Qi Gu, Chengcheng Han, Dengchang Zhao, Hui Su, Kefeng Zhang, Man Gao, Xi Su, Xiaodong Cai, Xunliang Cai, Yu Yang, Yunke Zhao

机构 * Meituan LongCat Team（美团LongCat团队）

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

Comments The code, dataset, and leaderboard are available at https://vitabench.github.io/

2510.15842 2025-10-20 cs.CL cs.CV 57%

Paper2Web: Let's Make Your Paper Alive!

Yuhang Chen, Tianpeng Lv, Siyi Zhang, Yixiang Yin, Yao Wan, Philip S. Yu, Dongping Chen

机构 * ONE Lab, Huazhong University of Science and Technology（华中科技大学）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）； University of Maryland（马里兰大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Under Review. Check https://github.com/YuhangChen1/Paper2All for the unified platform to streamline all academic presentation

2510.15306 2025-10-20 cs.AI 57%

WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation

Kuang-Da Wang, Zhao Wang, Yotaro Shimose, Wei-Yao Wang, Shingo Takamatsu

机构 * National Yang Ming Chiao Tung University, Sony Group Corporation（National Yang Ming Chiao Tung University, Sony集团）； Sony Group Corporation（Sony集团）

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

2510.04168 2025-10-20 cs.RO cs.SY eess.SY 50%

Learning to Capture Rocks using an Excavator: A Reinforcement Learning Approach with Guiding Reward Formulation

Amirmasoud Molaei, Mohammad Heravi, Reza Ghabcheloo

机构 * Faculty of Engineering and Natural Sciences, Tampere University（工程与自然科学学院，塔尔皮亚大学）

专题命中 Agent评测：agent(abstract)

2507.18251 2025-10-20 cs.GT 50%

On Pareto-Optimal and Fair Allocations with Personalized Bi-Valued Utilities

Jiarong Jin, Biaoshuai Tao

专题命中 Agent评测：agent(abstract)

Comments Accepted by WINE'25

2501.14686 2025-10-20 econ.TH 50%

The Division of Surplus and the Burden of Proof

Deniz Kattwinkel, Justus Preusser

专题命中 Agent评测：agent(abstract)

2510.15342 2025-10-20 cs.CV 50%

SHARE: Scene-Human Aligned Reconstruction

Joshua Li, Brendan Chharawala, Chang Shu, Xue Bin Peng, Pengcheng Xi

机构 * National Research Council Canada（加拿大国家研究理事会）； University of Waterloo（滑铁卢大学）； Simon Fraser University（西蒙 Fraser大学）

专题命中其他Agent ：autonomous agent(abstract)

Comments SIGGRAPH Asia Technical Communications 2025

1. 工作流自动化 16 篇

Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics

Retrofitting Service Dependency Discovery in Distributed Systems

Cloud-Enabled Virtual Prototypes

Impact of AI-Triage on Radiologist Report Turnaround Time: Real-World Time-Savings and Insights from Model Predictions

Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies

How to choose efficiently the size of the Bethe-Salpeter Equation Hamiltonian for accurate exciton calculations on supercells

2. 软件智能体 1 篇

Towards Error Centric Intelligence I, Beyond Observational Learning

3. GUI与网页智能体 4 篇

CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation

WebInject: Prompt Injection Attack to Web Agents

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation

4. 记忆与上下文管理 4 篇

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL

ES-C51: Expected Sarsa Based C51 Distributional Reinforcement Learning Algorithm

Active matter synchronization and synergetics

5. Agent评测 10 篇

MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation

Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language

When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue

CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Paper2Web: Let's Make Your Paper Alive!

WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation

Learning to Capture Rocks using an Excavator: A Reinforcement Learning Approach with Guiding Reward Formulation

On Pareto-Optimal and Fair Allocations with Personalized Bi-Valued Utilities

The Division of Surplus and the Burden of Proof

6. 其他Agent 1 篇

SHARE: Scene-Human Aligned Reconstruction