model · first seen 7 Oct 2026
process reward model
Also: PRM, dense rewards, token-level reward, process reward labels
A reward model that scores intermediate reasoning steps rather than only final outcomes.
Mentions per week
PapersCodeDiscussion
Earliest sources
- World Potential Model: Pretrained World Knowledge as Progress PotentialsPapers · 7 Oct 2026 · Jun Zhao, Jixin Tang, Yang Shu, Jinyang Wu, Yuyang Lu, Jingqi Tong, Hao Xu, Weif…
- BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token AggregationPapers · 7 Oct 2026 · Yingxiang Yang, Weihang Xiao, Zhunxuan Wang, Joshua Flashner, Niresh Agarwal
- RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward AdaptationPapers · 7 Oct 2026 · Hengbo Xiao, Boyao Zhang, Purui Liu, Yuxuan Zheng, Haoran Yin, Haibo Liu, Fan Zh…
- LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof VerificationPapers · 13 Oct 2026 · Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen, James Shiffer, Saadia Gabr…
- Adaptive-Group Process Rewards for GUI AgentsPapers · 13 Oct 2026 · Zirui Shang, Yang Liu, Xin Shu, Zhi Gao, Xinxiao Wu, Lifeng Fan
- Unlocking Token Rewards via Training-Free Reward AttributionPapers · 13 Oct 2026 · Sitong Wu, Haoru Tan, Bin Xia, Xichen Zhang, Jingyao Li, Shaofeng Zhang, Xiaojua…
Latest sources
- GPRM: Global Perspective Process Reward ModelPapers · 16 Nov 2026 · Zifan Zhang, Zhengbo Jiao, Shaobo Wang, Jing Zhou, Guoyi Li, Jiayi Chen, Wei Wan…
- Are Dense Rewards Worth Their Tokens in GRPO?Papers · 10 Nov 2026 · Vikash Singh, Weicong Chen, Debargha Ganguly, Yanyan Zhang, Mohsen Hariri, Sreeh…
- Plug-and-Play Verifier for Decoupling Process Reward in Stabilizing Long-Horizon Agentic ReasoningPapers · 6 Nov 2026 · Mingwei Xu, Jieyuan Pei, Binghao Tu, Hao Fang
- StrictPRMBench: A Replayable Evaluation Benchmark for Auditing Fixed-Score PRM AggregationPapers · 30 Oct 2026 · Pengfei Zheng
- Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their AnswersPapers · 27 Oct 2026 · Zongyuan Sun, Shuai Zhao, Yingjun Du, Ke Shu, Ziyue Zhu, Haoran Luo
- When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video EditingPapers · 26 Oct 2026 · Lei Zhao, Zongheng Cao, Xinyu Hu
- Implicit Beliefs as Scalable Process Rewards for Strategic PersuasionPapers · 24 Oct 2026 · Minqian Liu, Yuexi Shen, Heajun An, Qi Zhang, Pamela J. Wisniewski, Sang Won Lee…
- Multiple Importance Sampling for Guided Speculative InferencePapers · 23 Oct 2026 · Joseph Rowan, Ashish J. Khisti
- AdaPRA: Process Reward Agents with Adaptive Rubrics for Data SciencePapers · 23 Oct 2026 · Atharva Naik, Vivek Chari, Pol Llado, Daniel Fried, Carolyn Rosé, Benjamin Van…
- Predictive Long-Horizon Progress Modeling with Action-Aware QuantificationPapers · 23 Oct 2026 · Tianchi Xu, Yalin Zheng, Yangxin Zhu, Ruonan Ren, Zheng Fu, Yunlong Wang, Yuanxi…
- FLORA: An Open Model Suite for Scaling Robotics Data EnginesPapers · 22 Oct 2026 · Sicong Leng, Yunze Man, Zhiqi Li, Jing Wang, Yuhe Zhang, Ryan Punamiya, Siddhart…
- A Strong MoE Is All You Need for Process SupervisionPapers · 21 Oct 2026 · Guanzhi Deng, Zengyan Liu, Haibo Wang, Kuan Wu, Shing Yin Wong, Sichun Luo, Zhuo…