Learning to Self-Verify Makes Language Models Better Reasoners
National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Yuxin Chen, Yu Wang, Yi Zhang, Ziang Ye, Zhengzhou Cai, Yaorui Shi, Qi Gu, Hui Su, Xunliang Cai, Xiang Wang, An Zhang, Tat-Seng Chua
Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent capability asymmetry between generation and self-verification. In this work, we conduct an in-depth investigation of this asymmetry throughout training evolution and show that, even on the same task, improving generation does not lead to corresponding improvements in self-verification. Interestingly, we find that the reverse direction of this asymmetry behaves differently: learning to self-verify can effectively improve generation performance, achieving accuracy comparable to standard generation training while yielding more efficient and effective reasoning traces. Building on this observation, we further explore integrating self-verification into generation training by formulating a multi-task reinforcement learning framework, where generation and self-verification are optimized as two independent but complementary objectives. Extensive experiments across benchmarks and models demonstrate performance gains over generation-only training in both generation and verification capabilities.
Abstraction-of-Thought Makes Language Models Better Reasoners
Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能学院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tencent AI Lab（腾讯AI实验室）
Large Language Models are Better Reasoners with Self-Verification
The Laboratory of Cognition and Decision Intelligence for Complex Systems, IA, CAS（中国科学院自动化研究所复杂系统认知与决策智能实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）；Unisound（云知声）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Harbin Institute of Technology（哈尔滨工业大学）；Singapore Management University（新加坡管理学院）；Monash University（墨尔本大学）；Singapore University of Technology and Design（新加坡科技设计大学）；National University of Singapore（国立新加坡大学）
MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
Southern University of Science and Technology（南方科技大学）；The Hong Kong University of Science and Technology（香港科技大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Tongji University（同济大学）
Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
Xi’an Jiaotong-Liverpool University（西交利物浦大学）；University of Liverpool（利物浦大学）；University of Macau（澳门大学）；HKUST（香港科技大学）；Microsoft Research Asia（微软亚洲研究院）；Duke Kunshan University（昆山杜克大学）
Benchmarking Defeasible Reasoning with Large Language Models -- Initial Experiments and Future Directions
School of Computing and Engineering, University of Huddersfield（哈德斯菲尔德大学计算与工程学院）；Hellenic Mediterranean University（希腊地中海大学）；Leeds Beckett University（利兹贝克特大学）
SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Southern California（南加州大学）；University of Notre Dame（圣母大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of Chicago（芝加哥大学）；Microsoft（微软）
Scenarios and Recommendations for Ethical Interpretive AI
Advancing Machine and Human Reasoning (AMHR) Lab（推进机器与人类推理实验室）；Department of Computer Science and Engineering（计算机科学与工程系）；University of South Florida（南佛罗里达大学）
From Table to Cell: Attention for Better Reasoning with TABALIGN
University of California, Los Angeles（加州大学洛杉矶分校）；New Jersey Institute of Technology（新泽西理工学院）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；University of Manitoba（曼尼托巴大学）；SimpleWay；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
National University of Singapore（新加坡国立大学）；Southern University of Science and Technology（南方科技大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；City University of Hong Kong（香港城市大学）
