Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning
Fujian University of Technology（福建工程学院）；Fujian Provincial Key Laboratory of Big Data Mining and Applications（福建省大数据挖掘与应用重点实验室）；Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences（生物医学成像科学与系统重点实验室，中国科学院）
This study presents DiagCoT, a multi-stage framework that applies supervised fine-tuning to general-purpose vision-language models (VLMs) to emulate radiologists' stepwise diagnostic reasoning using only free-text reports. DiagCoT combines contrastive image-report tuning for domain alignment, chain-of-thought supervision to capture inferential logic, and reinforcement tuning with clinical reward signals to enhance factual accuracy and fluency. On the MIMIC-CXR benchmark, DiagCoT improved zero-shot disease classification AUC from 0.52 to 0.76 (absolute gain of 0.24), pathology grounding mIoU from 0.08 to 0.31 (absolute gain of 0.23), and report generation BLEU from 0.11 to 0.33 (absolute gain of 0.22). It outperformed state-of-the-art models including LLaVA-Med and CXR-LLAVA on long-tailed diseases and external datasets. By converting unstructured clinical narratives into structured supervision, DiagCoT offers a scalable approach for developing interpretable and diagnostically competent AI systems for radiology.
Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室）；Law&AI Lab, Zhejiang University（浙江大学法律与人工智能实验室）
SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
SIGS, Tsinghua University（清华大学信息科学与技术学院）；Southern University of Science and Technology（南方科技大学）；Guangdong Laboratory of AI and Digital Economy (SZ)（广东人工智能与数字经济实验室）；The Hong Kong University of Science and Technology（香港科技大学）；Peking University（北京大学）
Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Hunan Vanguard Group Corporation Co., Ltd.（湖南 Vanguard集团有限公司）；Huaneng Information Technology Co., Ltd.（华能信息技术有限公司）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；PowerChina Huadong Engineering Co., Ltd.（中国电建华东工程有限公司）
Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
ETH AI Center（ETH AI中心）；TU Darmstadt（达姆施塔特工业大学）；ETH Zurich（苏黎世联邦理工学院）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Ubiquitous Knowledge Processing Lab (UKP Lab)（普适知识处理实验室）；Department of Computer Science（计算机科学系）；Professorship for Learning Sciences and Higher Education（学习科学与高等教育教授席位）
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making
Tsinghua University（清华大学）；Meituan（美团）；Northeastern University（东北大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Meta AI；Wuhan University（武汉大学）
Large language models that are capable of zero or few-shot prompting approaches have given rise to the new research area of prompt engineering. Recent advances showed that for example Chain-of-Thought (CoT) prompts can improve arithmetic or common sense tasks significantly. We explore how such approaches fare with legal reasoning tasks and take the COLIEE entailment task based on the Japanese Bar exam for testing zero-shot/few-shot and fine-tuning approaches. Our findings show that while CoT prompting and fine-tuning with explanations approaches show improvements, the best results are produced…
Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
The Hong Kong University of Science and Technology（香港科学与技术大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Zhejiang University（浙江大学）；Peking University（北京大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Surrey（萨里大学）
TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
University of the Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；University of Electronic Science and Technology of China（电子科技大学）；The University of Hong Kong（香港大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；SenseTime Research（商汤科技研究院）
Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization
Data Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院数据科学系）；Electrical and Computer Engineering Department, Virginia Tech（弗吉尼亚理工大学电气与计算机工程系）；Computer Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院计算机科学系）；Computer Science Department, King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学计算机科学系）
The Challenge of Teaching Reasoning to LLMs Without RL or Distillation
Nvidia Corporation（Nvidia公司）；Institute for Artificial Intelligence Research（人工智能研究机构）；Faculty of Technical Sciences, University of Novi Sad（诺维萨德大学技术科学学院）；Department of Mathematics and Informatics, Faculty of Sciences, University of Novi Sad（诺维萨德大学科学学院数学与信息学系）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Chicago（芝加哥大学）；Georgia Institute of Technology（佐治亚理工学院）；Department of Computer and Information Science, School of Engineering and Applied Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）；Massachusetts Institute of Technology（麻省理工学院）
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Beijing University of Posts and Telecommunications（北京邮电大学）；The Hong Kong Polytechnic University（香港理工大学）；Tsinghua University（清华大学）；JIUTIAN Research（中移九天）；OpenBMB
The Allen Institute for AI（艾伦人工智能研究所）；Tel-Aviv University（特拉维夫大学）；Bar-Ilan University（巴伊兰大学）
To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. Recently, it has been shown that Transformer-based models succeed in consistent reasoning over explicit symbolic facts, under a "closed-world" assumption. However, in an open-domain setup, it is desirable to tap into the vast reservoir of implicit knowledge already encoded in the parameters of pre-trained LMs. In this work, we provide a first demonstration that LMs can be trained …
VIS Lab, University of Amsterdam（阿姆斯特丹大学VIS实验室）；FunAI Lab, University of Technology Nuremberg（纽伦堡技术大学FunAI实验室）；CSAIL, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）
