大模型推理能力

Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective

Daniel Franzen, Jan Disselhoff, David Hartmann

机构 * Johannes Gutenberg University Mainz（莱茵河畔明斯特大学） ； Lambda, Inc.（Lambda公司） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2025 camera-ready; 15 pages, 6 figures, 5 tables

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

Patara Trirat, Wonyong Jeong, Sung Ju Hwang

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2025, Project Page: https://deepauto-ai.github.io/automl-agent

Exploring Explanations Improves the Robustness of In-Context Learning

Ukyo Honda, Tatsushi Oka

机构 * CyberAgent ； Keio University（庆应大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACL 2025 (Main Conference)

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback

Thai Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments LAM Simulator framework for agentic data generation

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

机构 * Zhejiang University（浙江大学） ； Alibaba Group（阿里巴巴集团） ； Zhejiang Key Laboratory of Big Data Intelligent Computing（浙江省大数据智能计算重点实验室） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2025

Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations

Harshita Chopra, Chirag Shah

机构 * University of Washington（华盛顿大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

Jiahao Yuan, Zixiang Di, Zhiqing Cui, Guisong Yang, Usman Naseem

机构 * University of Shanghai for Science and Technology（上海理工大学） ； East China Normal University（华东师范大学） ； Nanjing University of Information Science and Technology（南京信息工程大学） ； Macquarie University（麦考瑞大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by ACL 2025 Main Conference

Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting

Wei Chen, Jiahao Zhang, Haipeng Zhu, Boyan Xu, Zhifeng Hao, Keli Zhang, Junjian Ye, Ruichu Cai

机构 * School of Computer Science, Guangdong University of Technology（广东技术大学计算机科学学院） ； College of Mathematics and Computer Science, Shantou University（汕头大学数学与计算机科学学院） ； Huawei Noah’s Ark Lab, Huawei（华为诺亚实验室） ； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by IJCAI 2025

Safety Alignment Can Be Not Superficial With Explicit Safety Signals

Jianwei Li, Jung-Eun Kim

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2025

Agentic Knowledgeable Self-awareness

Shuofei Qiao, Zhisong Qiu, Baochang Ren, Xiaobin Wang, Xiangyuan Ru, Ningyu Zhang, Xiang Chen, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2025

Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration

Shao Zhang, Xihuai Wang, Wenhao Zhang, Chaoran Li, Junru Song, Tingyu Li, Lin Qiu, Xuezhi Cao, Xunliang Cai, Wen Yao, Weinan Zhang, Xinbing Wang, Ying Wen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Meituan（美团） ； Intelligent Game and Decision Laboratory（智能游戏与决策实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by ACL 2025 Main. Camera Ready Version

Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making

Yihan Wang, Qiao Yan, Zhenghao Xing, Lihao Liu, Junjun He, Chi-Wing Fu, Xiaowei Hu, Pheng-Ann Heng

机构 * The Chinese University of Hong Kong（香港中文大学） ； Amazon（亚马逊） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li

机构 * Northwestern University（西北大学） ； University of Washington（华盛顿大学） ； Stanford University（斯坦福大学） ； Microsoft（微软） ； New York University（纽约大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Singapore Management University（新加坡国立管理学院） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Hybrid Voting-Based Task Assignment in Modular Construction Scenarios

Daniel Weiner, Raj Korpan

机构 * Computer Science Department Graduate Center, City University of New York（纽约城市大学研究生中心计算机科学系） ； Computer Science Department Hunter College and Graduate Center, City University of New York（纽约城市大学亨特学院及研究生中心计算机科学系） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Comments Accepted to Block by Block workshop at ICRA 2025

Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents

Tiannuo Yang, Zebin Yao, Bowen Jin, Lixiao Cui, Yusen Li, Gang Wang, Xiaoguang Liu

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

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction

Yuanchang Ye, Weiyan Wen

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by ICIPCA 2025

Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs

Lucas Maisonnave, Cyril Moineau, Olivier Bichler, Fabrice Rastello

机构 * Université Paris-Saclay CEA（巴黎-萨克雷大学CEA） ； List ； Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学） ； Inria（法国国家信息与自动化技术研究院） ； CNRS（法国国家科学研究中心） ； Grenoble INP（格勒诺布尔INP） ； LIG（实验室） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Distinguishing AI-Generated and Human-Written Text Through Psycholinguistic Analysis

Chidimma Opara

机构 * School of Computing, Engineering & Digital Technologies（计算、工程与数字技术学院） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8

HMCF: A Human-in-the-loop Multi-Robot Collaboration Framework Based on Large Language Models

Zhaoxing Li, Wenbo Wu, Yue Wang, Yanran Xu, William Hunt, Sebastian Stein

机构 * School of Electronics and Computer Science, University of Southampton（电子与计算机科学学院，南安普顿大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Planner

Aizierjiang Aiersilan

机构 * Aizierjiang Aiersilan（独立研究者） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments We are excited to announce that this paper has been accepted for oral presentation at the AAAI 2025 Main Conference. We are grateful for the insightful feedback from the reviewers and look forward to contributing to the discussions at AAAI

ClimaEmpact: Domain-Aligned Small Language Models and Datasets for Extreme Weather Analytics

Deeksha Varshney, Keane Ong, Rui Mao, Erik Cambria, Gianmarco Mengaldo

机构 * College of Design and Engineering, National University of Singapore（新加坡国立大学设计与工程学院） ； Department of Mathematics, National University of Singapore（新加坡国立大学数学系） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation

Jong Inn Park, Maanas Taneja, Qianwen Wang, Dongyeop Kang

机构 * University of Minnesota（明尼苏达大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Project page: https://minnesotanlp.github.io/scitalk-project-page/

Clarifying Ambiguities: on the Role of Ambiguity Types in Prompting Methods for Clarification Generation

Anfu Tang, Laure Soulier, Vincent Guigue

专题命中 规划推理 ：reasoning(abstract)；CoT(abstract)

Comments 11 pages, 3 figures. Accepted at SIGIR 2025

Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

Zhaolin Gao, Wenhao Zhan, Jonathan D. Chang, Gokul Swamy, Kianté Brantley, Jason D. Lee, Wen Sun

机构 * Cornell University（康奈尔大学） ； Princeton University（普林斯顿大学） ； Databricks Mosaic Research（Databricks 混合研究） ； Carnegie Mellon University（卡内基梅隆大学） ； Harvard University（哈佛大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming

Zixiao Zhao, Jing Sun, Zhe Hou, Zhiyuan Wei, Cheng-Hao Cai, Miao Qiao, Jin Song Dong

机构 * School of Computer Science, University of Auckland（计算机科学系，奥克兰大学） ； School of Information and Communication Technology, Griffith University（信息与通信技术系，格里菲斯大学） ； Beijing Institute of Technology（北京理工大学） ； Suzhou Industrial Park Monash Research Institute of Science and Technology（苏州工业园区莫纳什科学与技术研究所） ； School of Computing, National University of Singapore（计算系，新加坡国立大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts

Yunpeng Song, Jiawei Li, Yiheng Bian, Zhongmin Cai

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 39 (1), 2025

LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving

Hao Sha, Yao Mu, Yuxuan Jiang, Li Chen, Chenfeng Xu, Ping Luo, Shengbo Eben Li, Masayoshi Tomizuka, Wei Zhan, Mingyu Ding

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Large Language Model-based Decision-making for COLREGs and the Control of Autonomous Surface Vehicles

Klinsmann Agyei, Pouria Sarhadi, Wasif Naeem

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Comments This work has been accepted for publication at European Control Conference 2025, \c{opyright} IEEE 2025. Please cite the published version when available

RuleAgent: Discovering Rules for Recommendation Denoising with Autonomous Language Agents

Zongwei Wang, Min Gao, Junliang Yu, Yupeng Hou, Shazia Sadiq, Hongzhi Yin

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Comments 11 pages, 4 figures

ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation

Haoyu Fu, Diankun Zhang, Zongchuang Zhao, Jianfeng Cui, Dingkang Liang, Chong Zhang, Dingyuan Zhang, Hongwei Xie, Bing Wang, Xiang Bai

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)