通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2606.20075cs.LGcs.CL
什么使得潜在思维链中的监督有效：一种信息论分析
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院，东方理工大学）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）
Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories prone to semantic drift. In this work, we analyze Latent CoT from an information-theoretic perspective and identify this failure as a dual collapse: gradient attenuation along the optimization path and representational drift in the latent space. We further decompose process supervision into two complementary dimensions: Trajectory Supervision, which injects dense stepwise reasoning signals, and Space Supervision, which preserves the semantic structure of the latent manifold. Our analysis shows that rigid geometric compression can collapse the reasoning space, whereas generative reconstruction provides a more flexible semantic anchor that better preserves information capacity. To measure these effects, we introduce the Unified Latent Probe (ULP), which quantifies the mutual information between latent trajectories and explicit reasoning steps. Experiments reveal a clear Information-Performance Binding: reasoning accuracy depends on the information fidelity preserved in the latent chain. These findings provide a principled framework for latent reasoning supervision and suggest shifting from geometric imitation toward mutual information maximization. Our code is available at \href{https://github.com/EIT-NLP/Supervision-in-Latent-CoT}{this repository}.
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Mentorship for Alignment Research Students (MARS)（对齐研究 mentorship 项目）；University College London（伦敦大学学院）；Queen Mary University of London（伦敦女王学院）；ML Alignment & Theory Scholars (MATS)（对齐与理论学者）；Meridian Impact, Cambridge（剑桥 Meridian Impact）；Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Geodesic Research and University of Cambridge（Geodesic Research 和剑桥大学）
Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
Department of Computer Science and Engineering, The Ohio State University, USA（计算机科学与工程系，俄亥俄州立大学）；Department of Biomedical Informatics, The Ohio State University, USA（生物医学信息学系，俄亥俄州立大学）；Translational Data Analytics Institute, The Ohio State University, USA（转化数据分析研究所，俄亥俄州立大学）
Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室）；Institute of Digital Twin, EIT（数字孪生研究院）；Saarland University（萨尔兰大学）；Meituan Inc.（美团公司）
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Tencent BAC（腾讯BAC）；Shenzhen International Graduate School, Tsinghua University（深圳国际研究生院，清华大学）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；School of Mathematics and Statistics, University of Glasgow（格拉斯哥大学数学与统计学学院）
GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
Xidian University（西安电子科技大学）；Xi’an Jiaotong University（西安交通大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；University of Science and Technology of China（中国科学技术大学）
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
Sun Yat-Sen University（中山大学）；The Chinese University of Hong Kong（香港中文大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；National University of Singapore（新加坡国立大学）；University of Electronic Science and Technology of China（电子科技大学）；Beijing University of Posts and Telecommunieations（北京邮电大学）；Singapore Management University（新加坡管理大学）
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）
Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
Zhejiang University（浙江大学）；School of Engineering, Westlake University（西湖大学工程学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究所）；University College London（伦敦大学学院）
