大模型推理能力

Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML Monitoring

Gusseppe Bravo-Rocca, Peini Liu, Jordi Guitart, Rodrigo M Carrillo-Larco, Ajay Dholakia, David Ellison

机构 * Barcelona Supercomputing Center（巴塞罗那超级计算中心） ； Universitat Politècnica de Catalunya（加泰罗尼亚理工大学） ； Emory University（埃默里大学） 纠错

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

Comments Accepted at AAMAS 2025

Your Agent Can Defend Itself against Backdoor Attacks

Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting

机构 * Stony Brook University（石溪大学） ； Penn State University（宾夕法尼亚州立大学） 纠错

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

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Mengkang Hu, Yuhang Zhou, Wendong Fan, Yuzhou Nie, Bowei Xia, Tao Sun, Ziyu Ye, Zhaoxuan Jin, Yingru Li, Qiguang Chen, Zeyu Zhang, Yifeng Wang, Qianshuo Ye, Bernard Ghanem, Ping Luo, Guohao Li

机构 * The University of Hong Kong（香港大学） ； The University of Chicago（芝加哥大学） ； Northwestern University（西北大学） ； University of Cambridge（剑桥大学） 纠错

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

Comments Project Page: https://github.com/camel-ai/owl

The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation

Francisco Vargas, Alejandro González Coene, Gaston Escalante, Exequiel Lobón, Manuel Pulido

机构 * FaCENA, Universidad Nacional del Nordeste（法塞纳国立东北大学） ； Legalhub S. A.（Legalhub公司） ； Instituto de Modelado e Innovación Tecnológica, CONICET（模型与技术创新研究所，CONICET） 纠错

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

Journal ref Electronic Journal of SADIO; vol. 24 (2025), no. 1

Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage

Ruilin Liu, Zhixiao Zhao, Jieqiong Li, Chang Liu, Dongbo Wang

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

Comments We want to withdraw this paper due to data usage permission issues identified after submission. We discovered that our use of certain intangible cultural heritage materials required additional community permissions and institutional ethical approvals that were not obtained

Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models

Niccolò Turcato, Matteo Iovino, Aris Synodinos, Alberto Dalla Libera, Ruggero Carli, Pietro Falco

机构 * Department of Information Engineering, University of Padova（帕多瓦大学信息工程系） ； ABB Corporate Research（ABB企业研究） 纠错

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

SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition

Mengsong Wu, Di Zhang, Yuqiang Li, Dongzhan Zhou, Wenliang Chen

机构 * Soochow University（苏州大学） ； 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

Comments 11 pages, 5 figures

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Jie Zhou

机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； Pattern Recognition Center, WeChat AI, Tencent Inc, China（腾讯人工智能部模式识别中心） 纠错

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

Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks

Zijiang Yan, Hao Zhou, Jianhua Pei, Hina Tabassum

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

Comments Accepted in ICML 2025 Workshop on Machine Learning for Wireless Communication and Networks (ML4Wireless)

Enhancing Decision-Making of Large Language Models via Actor-Critic

Heng Dong, Kefei Duan, Chongjie Zhang

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

Comments Forty-second International Conference on Machine Learning (ICML 2025)

From Transformers to Large Language Models: A systematic review of AI applications in the energy sector towards Agentic Digital Twins

Gabriel Antonesi, Tudor Cioara, Ionut Anghel, Vasilis Michalakopoulos, Elissaios Sarmas, Liana Toderean

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

Improvement of Optimization using Learning Based Models in Mixed Integer Linear Programming Tasks

Xiaoke Wang, Batuhan Altundas, Zhaoxin Li, Aaron Zhao, Matthew Gombolay

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

Comments 4 pages, 4 figures

Language Models are Crossword Solvers

Soumadeep Saha, Sutanoya Chakraborty, Saptarshi Saha, Utpal Garain

机构 * Indian Statistical Institute, Kolkata（印度统计研究所，加尔各答） 纠错

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

Comments 10 pages, 3 figures, 6 Appendix. Accepted to NAACL 2025

Journal ref NAACL 2025 (Volume 1: Long Papers), pages 2074-2090

AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents

Fengze Liu, Haoyu Wang, Joonhyuk Cho, Dan Roth, Andrew W. Lo

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

FactsR: A Safer Method for Producing High Quality Healthcare Documentation

Victor Petrén Bach Hansen, Lasse Krogsbøll, Jonas Lyngsø, Mathias Baltzersen, Andreas Motzfeldt, Kevin Pelgrims, Lars Maaløe

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

When LLMs Team Up: The Emergence of Collaborative Affective Computing

Wenna Lai, Haoran Xie, Guandong Xu, Qing Li, S. Joe Qin

机构 * Department of Computing, Hong Kong Polytechnic University（香港理工大学计算机系） ； School of Data Science, Lingnan University（岭南大学数据科学学院） ； School of Computer Science and the Data Science Institute, University of Technology Sydney（悉尼大学计算机科学学院和数据科学研究所） ； Education University of Hong Kong（香港教育大学） 纠错

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

Comments 20 pages, 7 figures, and 3 tables

Bottom-Up Perspectives on AI Governance: Insights from User Reviews of AI Products

Stefan Pasch

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

HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gym

Ngoc La, Ruaridh Mon-Williams, Julie A. Shah

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

Comments Accepted to Proceedings of ICAPS 2025

Enhancing Vision Transformer Explainability Using Artificial Astrocytes

Nicolas Echevarrieta-Catalan, Ana Ribas-Rodriguez, Francisco Cedron, Odelia Schwartz, Vanessa Aguiar-Pulido

机构 * University of Miami（迈阿密大学） ； University of A Coruña（阿罗乌纳大学） 纠错

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

Comments LXCV Workshop at IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2025

Gender and Positional Biases in LLM-Based Hiring Decisions: Evidence from Comparative CV/Résumé Evaluations

David Rozado

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

Active Inference Meeting Energy-Efficient Control of Parallel and Identical Machines

Yavar Taheri Yeganeh, Mohsen Jafari, Andrea Matta

机构 * Politecnico di Milano（米兰理工学院） ； Rutgers University（罗格斯大学） 纠错

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

Comments Accepted at the 10th International Conference on Machine Learning, Optimization, and Data Science

Deep Active Inference Agents for Delayed and Long-Horizon Environments

Yavar Taheri Yeganeh, Mohsen Jafari, Andrea Matta

机构 * Politecnico di Milano（米兰理工学院） ； Rutgers University（罗切斯特大学） 纠错

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

A Cognitive Writing Perspective for Constrained Long-Form Text Generation

Kaiyang Wan, Honglin Mu, Rui Hao, Haoran Luo, Tianle Gu, Xiuying Chen

机构 * MBZUAI ； University of Chinese Academy of Sciences（中国科学院大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

Comments 13 pages, 6 figures

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

Hao Kang, Qingru Zhang, Han Cai, Weiyuan Xu, Tushar Krishna, Yilun Du, Tsachy Weissman

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

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI

Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee

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

Comments 35 Pages, 8 Figures, 6 Tables

O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering

Jianbiao Mei, Tao Hu, Daocheng Fu, Licheng Wen, Xuemeng Yang, Rong Wu, Pinlong Cai, Xinyu Cai, Xing Gao, Yu Yang, Chengjun Xie, Botian Shi, Yong Liu, Yu Qiao

机构 * Zhejiang University（浙江大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； University of Science and Technology of China（中国科学技术大学） ； Fudan University（复旦大学） ； State Key Laboratory of Industrial Control Technology（工业控制技术国家重点实验室） 纠错

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

Comments 25 pages, 9 figures

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

Ziliang Wang, Xuhui Zheng, Kang An, Cijun Ouyang, Jialu Cai, Yuhang Wang, Yichao Wu

机构 * SenseTime（深睿科技） ； Nanjing University（南京大学） ； Shenzhen University（深圳大学） 纠错

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

Comments 20 pages, 6 figures

IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig, Arman Cohan

机构 * TCS Research（TCS研究院） ； Yale University（耶鲁大学） 纠错

专题命中 规划推理 ：test-time compute(abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 (System Demonstration Track)

Thought calibration: Efficient and confident test-time scaling

Menghua Wu, Cai Zhou, Stephen Bates, Tommi Jaakkola

机构 * Department of Computer Science（计算机科学系） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors

Tazeek Bin Abdur Rakib, Ambuj Mehrish, Lay-Ki Soon, Wern Han Lim, Soujanya Poria

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