AI Agent

Inefficiencies of Meta Agents for Agent Design

Batu El, Mert Yuksekgonul, James Zou

机构 * Stanford University（斯坦福大学） 纠错

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

A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning

Zhengpeng Xie, Yulong Zhang

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

Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography

Jiuan Zhou, Yu Cheng, Yuan Xie, Zhaoxia Yin

专题命中 Agent评测 ：agent(title,abstract)

Comments 15 pages, 9 figures

Spiral of Silence in Large Language Model Agents

Mingze Zhong, Meng Fang, Zijing Shi, Yuxuan Huang, Shunfeng Zheng, Yali Du, Ling Chen, Jun Wang

机构 * AAII, University of Technology Sydney（AAII，悉尼大学） ； University of Liverpool（利物浦大学） ； King’s College London（伦敦国王学院） ； University College London（伦敦大学学院） 纠错

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

Comments Accepted to EMNLP 2025 (Findings)

GPS-MTM: Capturing Pattern of Normalcy in GPS-Trajectories with self-supervised learning

Umang Garg, Bowen Zhang, Anantajit Subrahmanya, Chandrakanth Gudavalli, BS Manjunath

机构 * ECE Department（电子工程系） ； University of California（加州大学） 纠错

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

Comments 4 pages, 2 figures

Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations

Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla

机构 * MPI-SWS（马克斯·普朗克研究所-斯图加特） 纠错

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

GPT-5 Model Corrected GPT-4V's Chart Reading Errors, Not Prompting

Kaichun Yang, Jian Chen

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； The Ohio State University（俄亥俄州立大学） 纠错

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

Nonparametric Bellman Mappings for Value Iteration in Distributed Reinforcement Learning

Yuki Akiyama, Konstantinos Slavakis

机构 * Institute of Science Tokyo, Department of Information and Communications Engineering（东京科学研究所信息与通信工程系） 纠错

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

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Fenghe Tang, Chengqi Dong, Wenxin Ma, Zikang Xu, Heqin Zhu, Zihang Jiang, Rongsheng Wang, Yuhao Wang, Chenxu Wu, Shaohua Kevin Zhou

专题命中 Agent评测 ：agent(abstract)

Comments 54 pages. The project can be accessed at: https://fenghetan9.github.io/ubench. Code is available at: https://github.com/FengheTan9/U-Bench

M^3RS: Multi-robot, Multi-objective, and Multi-mode Routing and Scheduling

Ishaan Mehta, Junseo Kim, Sharareh Taghipour, Sajad Saeedi

机构 * Toronto Metropolitan University（多伦多 Metropolitan 大学） ； Delft University of Technology（代尔夫特技术大学） ； University College London（伦敦大学学院） 纠错

专题命中 Agent评测 ：agent(abstract)

Comments Under review

Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz

Frederic Gmeiner, Kenneth Holstein, Nikolas Martelaro

专题命中 Agent评测 ：agent(abstract)

Comments 18 pages, 5 figures, 4 tables

Consensus as cooling: a granular gas model for continuous opinions on structured networks

Carlos Uriarte, Pablo Rodriguez-Lopez, Nagi Khalil

专题命中 Agent评测 ：agent(abstract)

Comments 25 pages, 7 figures

Approximately Envy-free and Equitable Allocations of Indivisible Items for Non-monotone Valuations

Vittorio Bilò, Martin Loebl, Cosimo Vinci

专题命中 Agent评测 ：agent(abstract)

Comments Updated title; improved presentation of results and notation; corrected minor inaccuracies in proofs and discussions; updated references