Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the generated text, or the hidden-state vectors across model layers within one step. We introduce PRISM (Probabilistic Reasoning Inspection through Semantic and Implicit Modeling), a framework and diagnostic tool for jointly analyzing both levels, providing a unified view of how reasoning evolves across steps and layers. Across multiple reasoning models and benchmarks, PRISM uncovers systematic patterns in the reasoning process, showing that failed trajectories are more likely to become trapped in unproductive verification loops and further diverge into distinct modes such as overthinking and premature commitment, which behave differently once a candidate answer is reached. It further reveals how prompting reshapes reasoning behavior beyond aggregate accuracy by altering both semantic transitions and internal computational patterns. By modeling reasoning trajectories as structured processes, PRISM makes these behaviors observable and analyzable rather than relying solely on final-task accuracy. Taken together, these insights position PRISM as a practical tool for analyzing and diagnosing reasoning processes in LLMs.
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学 Gallagher人工智能学院）；Beijing Key Laboratory of Research on Large Models（北京大型模型研究关键实验室）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心）
Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
Department of Computing, The Hong Kong Polytechnic University（计算机系，香港理工大学）；Ningbo Digital Twin Institute, Eastern Institute of Technology（宁波数字孪生研究院，东部技术研究所）
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（人工智能安全国家重点实验室，计算技术研究所，中国科学院，北京）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京）
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人机混合增强智能国家重点实验室，人工智能与机器人研究院，西安交通大学）
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
School of AI, Shanghai Jiao Tong University（上海交通大学人工智能学院）；Kling Team, Kuaishou Technology（快手科技 Kling 团队）；Peking University（北京大学）；HKUST（香港科技大学）；CASIA（中国科学院自动化研究所）；Nanjing University（南京大学）；Renmin University of China（中国人民大学）；Tsinghua University（清华大学）
本文提出LatentOmni框架，通过统一的音频-视觉潜在空间进行多模态推理，利用特征级监督和Omni-Sync Position Embedding保持时间一致性，从而在多个音频-视觉推理基准测试中取得最佳性能。
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）；Zhongguancun Academy（中关村学院）
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）
Unlocking the Working Memory of Large Language Models for Latent Reasoning
ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria（林茨ELLIS单元和LIT AI实验室，机器学习研究所，约翰·凯撒大学林茨，奥地利）；NXAI GmbH, Linz, Austria（NXAI公司，林茨，奥地利）
Parallel Test-Time Scaling for Latent Reasoning Models
Hong Kong Polytechnic University（香港理工大学）；Shandong Jianzhu University（山东建筑大学）；University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；NLCo Lab, Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院NLCo实验室）；Department of Automation, Tsinghua University（清华大学自动化系）；Shanghai Jiao Tong University（上海交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of California, Los Angeles（加州大学洛杉矶分校）
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
Tongji University（同济大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Nanjing University（南京大学）
