AI Agent

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Tim Z. Xiao, Johannes Zenn, Zhen Liu, Weiyang Liu, Robert Bamler, Bernhard Schölkopf

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments Technical Report v1 (21 pages, 14 figures)

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Yujia Qin, Yining Ye, Yaxi Lu, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

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

Comments Accepted by ACL 2025 Main Conference

Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis

Jan Sellner, Alexander Studier-Fischer, Ahmad Bin Qasim, Silvia Seidlitz, Nicholas Schreck, Minu Tizabi, Manuel Wiesenfarth, Annette Kopp-Schneider, Janne Heinecke, Jule Brandt, Samuel Knödler, Caelan Max Haney, Gabriel Salg, Berkin Özdemir, Maximilian Dietrich, Maurice Stephan Michel, Felix Nickel, Karl-Friedrich Kowalewski, Lena Maier-Hein

机构 * Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany（智能医疗系统部门，德国癌症研究中心（DKFZ），海德堡，德国） ； Helmholtz Information and Data Science School for Health, Heidelberg/Karlsruhe, Germany（健康信息与数据科学学院，海德堡/卡尔斯鲁厄，德国） ； Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany（数学与计算机科学学院，海德堡大学，海德堡，德国） ； National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and university medical center Heidelberg（肿瘤疾病国家研究中心（NCT），海德堡NCT，德国癌症研究中心（DKFZ）与海德堡大学医学中心的合作机构） ； Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany（普通外科、 visceral外科及移植外科部门，海德堡大学医院，海德堡，德国） ； Department of Urology and Urosurgery, Medical Faculty of the University of Heidelberg, University Medical Center Mannheim, Mannheim, Germany（泌尿外科与泌尿外科部门，海德堡大学医学院，曼海姆大学医学中心，曼海姆，德国） ； Division of Intelligent Systems and Robotics in Urology (ISRU), German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany（泌尿外科智能系统与机器人部门（ISRU），德国癌症研究中心（DKFZ）海德堡，海德堡，德国） ； DKFZ Hector Cancer Institute at the University Medical Center Mannheim, Mannheim, Germany（德国癌症研究中心（DKFZ）曼海姆癌症研究所，曼海姆，德国） ； Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany（生物统计学部门，德国癌症研究中心（DKFZ），海德堡，德国） ； Heidelberg University, Medic（海德堡大学，Medic） 纠错

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

Comments Jan Sellner and Alexander Studier-Fischer contributed equally to this work

CodeContests+: High-Quality Test Case Generation for Competitive Programming

Zihan Wang, Siyao Liu, Yang Sun, Hongyan Li, Kai Shen

机构 * ByteDance Seed（字节跳动种子） ； Peking University（北京大学） 纠错

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

Comments 28 pages, 7 figures

IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

Hanyu Li, Haoyu Liu, Tingyu Zhu, Tianyu Guo, Zeyu Zheng, Xiaotie Deng, Michael I. Jordan

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

CORE: Constraint-Aware One-Step Reinforcement Learning for Simulation-Guided Neural Network Accelerator Design

Yifeng Xiao, Yurong Xu, Ning Yan, Masood Mortazavi, Pierluigi Nuzzo

机构 * University of California, Berkeley（加州大学伯克利分校） ； Futurewei Technologies（未来科技） 纠错

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

Comments Preprint. 10 pages + appendix. Submitted to NeurIPS 2025

Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation

Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani, Mohammadali Mohammadkhani, Bardia Mohammadi, Omid Ghahroodi, Mahdieh Soleymani Baghshah, Ehsaneddin Asgari

机构 * Computer Engineering Department, Sharif University of Technology（沙斐大学计算机工程系） ； College of Interdisciplinary Science and Technology, University of Tehran（德黑兰大学跨学科科学与技术学院） ； Computer Engineering Department, K.N. Toosi University of Technology（技术学院计算机工程系） ； Qatar Computing Research Institute（卡塔尔计算研究院） 纠错

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

Comments GitHub repository: https://github.com/llm-lab-org/Multimodal-RAG-Survey

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro, Aaron Courville, Glen Berseth

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

Comments Accepted to ICML 2025

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

Suhana Bedi, Hejie Cui, Miguel Fuentes, Alyssa Unell, Michael Wornow, Juan M. Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, Hao Qiu, Shrey Jain, Leonardo Schettini, Mehr Kashyap, Jason Alan Fries, Akshay Swaminathan, Philip Chung, Fateme Nateghi, Asad Aali, Ashwin Nayak, Shivam Vedak, Sneha S. Jain, Birju Patel, Oluseyi Fayanju, Shreya Shah, Ethan Goh, Dong-han Yao, Brian Soetikno, Eduardo Reis, Sergios Gatidis, Vasu Divi, Robson Capasso, Rachna Saralkar, Chia-Chun Chiang, Jenelle Jindal, Tho Pham, Faraz Ghoddusi, Steven Lin, Albert S. Chiou, Christy Hong, Mohana Roy, Michael F. Gensheimer, Hinesh Patel, Kevin Schulman, Dev Dash, Danton Char, Lance Downing, Francois Grolleau, Kameron Black, Bethel Mieso, Aydin Zahedivash, Wen-wai Yim, Harshita Sharma, Tony Lee, Hannah Kirsch, Jennifer Lee, Nerissa Ambers, Carlene Lugtu, Aditya Sharma, Bilal Mawji, Alex Alekseyev, Vicky Zhou, Vikas Kakkar, Jarrod Helzer, Anurang Revri, Yair Bannett, Roxana Daneshjou, Jonathan Chen, Emily Alsentzer, Keith Morse, Nirmal Ravi, Nima Aghaeepour, Vanessa Kennedy, Akshay Chaudhari, Thomas Wang, Sanmi Koyejo, Matthew P. Lungren, Eric Horvitz, Percy Liang, Mike Pfeffer, Nigam H. Shah

机构 * Stanford University School of Medicine（斯坦福大学医学院） ； Stanford Health Care（斯坦福健康系统） ； Center for Research on Foundation Models (CRFM) & Department of Computer Science（基础模型研究中心（CRFM）及计算机科学系） ； Microsoft Corporation（微软公司） ； Stanford Institute for Human-Centered AI（斯坦福大学人本人工智能研究所） 纠错

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

Reinforcement Learning for Hanabi

Nina Cohen, Kordel K. France

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

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

White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs

Yixin Wan, Kai-Wei Chang

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

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

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Yilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang, Li Shen, Xueqian Wang, Dacheng Tao

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

Comments ICML 2025

Conversational Exploration of Literature Landscape with LitChat

Mingyu Huang, Shasha Zhou, Yuxuan Chen, Ke Li

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

COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents

Arun Verma, Indrajit Saha, Makoto Yokoo, Bryan Kian Hsiang Low

机构 * Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联合研究技术联盟） ； Faculty of ISEE, Kyushu University（九州大学信息科学系） ； Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） 纠错

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

Comments This paper proposes a contextual bandit algorithm that prevents strategic agents from misreporting while having approximate incentive compatibility and a sub-linear regret guarantee

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, William Yang Wang

机构 * Nanyang Technological University（南洋理工大学） ； University of California, Santa Barbara（加州大学圣芭芭拉分校） ； National University of Singapore（新加坡国立大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Arizona（亚利桑那大学） 纠错

专题命中 Agent评测 ：workflow(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ACL 2025 main conference. Code and data are at https://github.com/bobxwu/AntiLeakBench

Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies

Arun Verma, Indrajit Saha, Makoto Yokoo, Bryan Kian Hsiang Low

机构 * Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联合研究技术联盟） ； Faculty of ISEE, Kyushu University（九州大学信息科学与工程学院） ； Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） 纠错

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

Comments We propose a contextual bandit algorithm for online fair division problems involving multiple agents and a large number of items, each with only a few copies

X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents

Weiqi Wu, Hongqiu Wu, Hai Zhao

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） 纠错

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

Comments Accepted to ACL 2025 Main Conference

A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment

Brett Bissey, Kyle Gatesman, Walker Dimon, Mohammad Alam, Luis Robaina, Joseph Weissman

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

Algorithmic Control Improves Residential Building Energy and EV Management when PV Capacity is High but Battery Capacity is Low

Lennart Ullner, Alona Zharova, Felix Creutzig

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

Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies

Kevin Li, Marinka Zitnik

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Harvard Medical School（哈佛医学院） ； Kempner Institute at Harvard University（哈佛大学凯普勒研究所） 纠错

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

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes

Bhargav Ganguly, Yang Xu, Vaneet Aggarwal

机构 * Association for the Advancement of Artificial Intelligence（美国人工智能协会） 纠错

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

Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking

Robin D. Pesl, Jerin G. Mathew, Massimo Mecella, Marco Aiello

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

Comments arXiv admin note: substantial text overlap with arXiv:2411.19804

Learning Transformer-based World Models with Contrastive Predictive Coding

Maxime Burchi, Radu Timofte

机构 * Computer Vision Lab, CAIDAS & IFI, University of Würzburg（计算机视觉实验室、CAIDAS与IFI、乌尔姆大学） 纠错

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

ReviewEval: An Evaluation Framework for AI-Generated Reviews

Madhav Krishan Garg, Tejash Prasad, Tanmay Singhal, Chhavi Kirtani, Murari Mandal, Dhruv Kumar

机构 * IIIT Delhi（德里印度理工学院） ； KIIT Bhubaneswar（比哈尔理工学院） ； BITS Pilani（比什努学院） 纠错

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

Comments Under review: 8 pages, 2 figures, 5 tables, 9 pages for appendix

Development and Validation of Engagement and Rapport Scales for Evaluating User Experience in Multimodal Dialogue Systems

Fuma Kurata, Mao Saeki, Masaki Eguchi, Shungo Suzuki, Hiroaki Takatsu, Yoichi Matsuyama

机构 * Waseda University, Tokyo, Japan（大阪大学） 纠错

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

Journal ref Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology, Hokkaido, Japan, 2024

BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research

Zifeng Wang, Benjamin Danek, Jimeng Sun

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

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

Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One

Yiwen Song, Qianyue Hao, Qingmin Liao, Jian Yuan, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系、BNRist、清华大学） 纠错

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

TARGET: Benchmarking Table Retrieval for Generative Tasks

Xingyu Ji, Parker Glenn, Aditya G. Parameswaran, Madelon Hulsebos

机构 * UC Berkeley（伯克利大学） ； Capital One（Capital One公司） ； CWI（荷兰代尔夫特理工大学） 纠错

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

Adaptive Reward Design for Reinforcement Learning

Minjae Kwon, Ingy ElSayed-Aly, Lu Feng

机构 * The Department of Computer Science University of Virginia（计算机科学系大学弗吉尼亚大学） 纠错

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

Comments UAI 2025 Camera Ready Version

Exploratory Diffusion Model for Unsupervised Reinforcement Learning

Chengyang Ying, Huayu Chen, Xinning Zhou, Zhongkai Hao, Hang Su, Jun Zhu

机构 * Department of Computer Science & Technology, Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University（计算机科学与技术系、人工智能研究院、BNRist中心、清华-博世联合机器学习中心、THBI实验室、清华大学） 纠错

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