Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-language models (VLMs). Sparse binary outcome rewards, however, score only final correctness and cannot identify which intermediate steps contributed to it; in multimodal tasks, they may also reward answers driven by linguistic priors rather than visual evidence. Process reward models (PRMs) densify supervision but usually require process annotations, auxiliary models, or inference-time search. In this paper, we introduce Stepwise Marginal Information Gain (MIG), an intrinsic process reward computed from the policy itself. MIG measures how each structured reasoning prefix changes the length-normalized, teacher-forced log-likelihood of the reference answer. A monotonic historical watermark rewards only new likelihood maxima, avoiding duplicate credit after sub-record detours. We combine this signal with outcome and format rewards and a gated self-distillation objective that retains only structurally valid and correct trajectories. For VLMs, a real-versus-blank likelihood gate down-weights rewards when answers remain predictable without the image. Across eight task-specific benchmarks, the full method exceeds outcome-only GRPO in every single-run comparison. In broad-data transfer, it improves average accuracy by up to 4.8 points over binary-reward training and gains 12.6 points on MathVerse. At 7B, it exceeds an external PRM-BoN@16 baseline by 12.9 points on vision-language transfer without inference-time reranking. These results support policy-derived stepwise credit as an annotation-free alternative to explicit process reward modeling.
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
MILA – Quebec AI Institute & ILLS（魁北克人工智能研究所与ILLs）；Université Paris-Saclay & CentraleSupélec & CNRS（巴黎-萨克雷大学及CentraleSupélec与CNRS）；Air Liquide；Sorbonne Université & ISIR & CNRS（索邦大学及ISIR与CNRS）；Sapienza, University of Rome（罗马大学Sapienza）
Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
Korea University（韩国大学）；ETH Zürich（苏黎世联邦理工学院）；Yale University（耶鲁大学）；AIGEN Sciences（AIGEN公司）；Hanyang University College of Medicine（翰雅大学医学院）；University of Ulsan College of Medicine（釜山大学医学院）
Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision
Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Peking University（北京大学）；School of Information, Renmin University of China（中国人民大学信息学院）；Harbin Institute of Technology（哈尔滨工业大学）；North China Electric Power University（华北电力大学）；GDS Holdings Limited（GDS控股有限公司）
Rubric-Guided Process Reward for Stepwise Model Routing
University of Science and Technology of China（中国科学技术大学）；Southeast University（东南大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
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）
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所认知与决策智能复杂系统重点实验室）；China Merchants Bank（中国 Merchants 银行）
Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling
Zhiyuan College, Shanghai Jiao Tong University（上海交通大学紫阳学院）；National University of Singapore（新加坡国立大学）；Tongji University（同济大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Enhancing Table Reasoning with Deterministic Table-State Rewards
University of California, Los Angeles（加州大学洛杉矶分校）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；University College London（伦敦大学学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Manitoba（曼尼托巴大学）
Promoting Efficient Reasoning with Verifiable Stepwise Reward
Meituan（美团）；Fudan University（复旦大学）；Beijing Institute of Technology（北京理工大学）；University of Science and Technology of China（中国科学技术大学）；East China Normal University（华东师范大学）
