Process Reward Models

Also known as PRM

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 91

All topics

VisCritic: Visual State Comparison as Process Reward for GUI Agents
Jun 23, 2026Jiachen QianProcess Reward Models GUI Agents
City University of Hong Kong
Learning Process Rewards via Success Visitation Matching for Efficient RL
Jun 22, 2026Raymond Tsao, Andrew Wagenmaker, Sergey LevineProcess Reward Models Credit Assignment in RL
UC Berkeley
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
Jun 20, 2026Pengzhi Yang, Xinyu Wang, Pengyu Jing +7Long-Horizon Robotic Manipulation Robot Skill Learning
† NUS Human-Centered Robotic Lab · ‡ Booking.com · § University of Cambridge +1
ARCO: Adaptive Rubric with Co-Evolution for Multi-Step LLM-Based Agents
Jun 19, 2026Zihang Tian, Jingsen Zhang, Rui Li +3Process Reward Models Credit Assignment in RL
Renmin University of China
VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools
Jun 17, 2026Amirul Rahman, Mohammed Sabih AlsharariPAC-Bayesian Generalization Bounds Process Reward Models
University of Malaya
From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification
Jun 11, 2026Rongxin Yang, Shenghong He, Siyuan Zhu +1Agentic RL Process Reward Models
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning
Jun 8, 2026Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian +6Process Reward Models RL for Language Model Reasoning
University of Maryland, College Park · Capital One · University of Central Florida
Improving Multimodal Reasoning via Worst Dimension Optimization
Jun 5, 2026Haocheng Lv, Huaping Zhang, Qiuchi Li +2Process Reward Models Multimodal Reasoning
Beijing Institute of Technology
Self-evolving LLM agents with in-distribution Optimization
Jun 5, 2026Yudi Zhang, Meng Fang, Zhenfang Chen +1Reinforcement Learning Process Reward Models
Eindhoven University of Technology, Netherlands · University of Liverpool, United Kingdom · MIT-IBM Watson AI Lab.
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning
Jun 5, 2026Yuhang Zhou, Yixin Cao, Guangnan YeProcess Reward Models RL for Language Model Reasoning
Fudan University · Shanghai Innovation Institute
StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents
Jun 5, 2026Haojie Hao, Longkun Hao, Yihang Lou +8Reinforcement Learning RL for GUI Agents
Beihang University · Peking University · Renmin University of China +4
SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification
Jun 3, 2026Xiangyu Zhao, Henry Hengyuan Zhao, Yiheng Wang +7Process Reward Models Scientific Reasoning
The Hong Kong Polytechnic University · National University of Singapore · Shanghai AI Lab +3
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
Jun 2, 2026Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi +2RL for Code Generation Process Reward Models
IBM Research San Jose, CA, USA
CAPER: Clause-Aligned Process Supervision for Text-to-SQL
Jun 2, 2026Lujie Ban, Jiasheng Shi, Jinyang Li +3Process Reward Models RL for Language Model Reasoning
The Chinese University of Hong Kong, Shenzhen · The University of Hong Kong · Northwestern Polytechnical University +1
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
Jun 2, 2026Zheng Liu, Longxiang Zhang, Xintong Wang +8Reward Modeling Process Reward Models
Tsinghua University · Alibaba Group · Peking University +1
From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting
Jun 2, 2026Mingyang Liu, Qingcan Kang, Yuke Wang +6Process Reward Models Financial Forecasting
Department of Computer Science, City University of Hong Kong · Work done as an intern in Huawei Noah’s Ark Lab. · Huawei Noah’s Ark Lab
Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
May 31, 2026Shihao Ji, Haotao Tan, Zihui Song +1Reward Modeling Automated Theorem Proving
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
May 30, 2026Zihan Chen, Yiming Zhang, Wenxiang Geng +2Process Reward Models RL for Language Model Reasoning
1HFIPS, Chinese Academy of Sciences · University of Science and Technology of China
EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing
May 30, 2026Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1Process Reward Models Language Model Calibration
Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology · Department of Civil, Construction & Environmental Engineering, Iowa State University
VeriGate: Verifier-Gated Step-Level Supervision for GRPO
May 28, 2026Aakriti Agrawal, Minghui Liu, Furong HuangProcess Reward Models RL for Language Model Reasoning
University of Maryland, College Park
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
May 28, 2026Shicheng Fan, Haochang Hao, Dehai Min +3Process Reward Models RL for Language Model Reasoning
University of Illinois Chicago
Rubric-Guided Process Reward for Stepwise Model Routing
May 28, 2026Shenghao Ye, Yu Guo, Zhengheng Li +2Process Reward Models RL for Language Model Reasoning
University of Science and Technology of China · Southeast University
PRO-CUA: Process-Reward Optimization for Computer Use Agents
May 27, 2026Yifei He, Rui Yang, Hao Bai +2Reinforcement Learning Process Reward Models
University of Illinois Urbana-Champaign
What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
May 25, 2026Yuelyu Ji, Min Gu Kwak, Hang Zhang +3Reward Hacking Retrieval-Augmented Generation
University of Pittsburgh, Pittsburgh, PA, USA
StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering
May 23, 2026Yuelyu Ji, Zhuochun Li, Hui Ji +1Multi-Hop QA LLM Answer Verification
School of Computing and Information, University of Pittsburgh
Learning to Reason Efficiently with A* Post-Training
May 23, 2026Andreas Opedal, Francesco Ignazio Re, Abulhair Saparov +3Process Reward Models RL for Language Model Reasoning
αETH Zürich · γPurdue University · βMPI for Intelligent Systems, Tübingen
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
May 22, 2026Sirui Chen, Lei Xu, Yuying Zhao +6Process Reward Models RL for Language Model Reasoning
1Tongji University · 2Shanghai AI Laboratory · 3Nanyang Technological University +3
Process Rewards with Learned Reliability
May 15, 2026Jinyuan Li, Langlin Huang, Chengsong Huang +5Reward Modeling Process Reward Models
Washington University in St. Louis · Singapore University of Technology and Design
CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
May 13, 2026Tengda Guo, Jie Leng, Hanlei Li +6Process Reward Models Visual Reasoning
Tsinghua University · Peking University · Zhejiang University of Technology
Verifiable Process Rewards for Agentic Reasoning
May 11, 2026Huining Yuan, Zelai Xu, Huaijie Wang +6Process Reward Models Credit Assignment in RL
Tsinghua University

Jun 23, 2026, cs.CVJ/K move · Enter open · S save

VisCritic: Visual State Comparison as Process Reward for GUI Agents

Jiachen Qian

City University of Hong Kong

Process Reward Models GUI Agents Multimodal Reward Modeling

Open paper AskPDF arXiv

GUI agents powered by vision-language models show strong potential for automating digital tasks, yet frequently fail in long-horizon scenarios due to the absence of step-level verification. Existing process reward models verify actions through textual reasoning alone, missing the visual nature of GUI state changes. We introduce VisCritic, a visual process reward framework that verifies agent actions by directly comparing pre-action and post-action screenshots in visual feature space. VisCritic employs a Siamese vision transformer to extract change-aware representations, coupled with an Action-Aware Critic Head that jointly evaluates action success, task progress, and error type. A critic-training data construction pipeline generates weakly supervised samples from existing trajectories without additional human labels for critic training. Experiments and offline analyses across five benchmarks demonstrate that VisCritic serves as a plug-and-play enhancement for diverse GUI agents, generally improving benchmark metrics while providing visual diagnostic cues.

Momentum

Related topics

Latest papers 91