Unsupervised PRMs derived from LLM probabilities achieve up to 15% better error detection than LLM judges and match supervised PRMs in verification and RL tasks.
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
DataPRM is a new process reward model for data analysis agents that detects silent errors via environment interaction and ternary rewards, yielding 7-11% gains on benchmarks and further RL improvements.
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
OpenClaw-RL recovers evaluative and directive signals from next-state interactions to enable online RL training of agents across terminal, GUI, SWE, and tool environments via a server-client architecture and hybrid objective.
STOP is a new learnable internal path-pruning technique that improves efficiency and accuracy of parallel reasoning in LRMs under fixed compute budgets.
citing papers explorer
-
Unsupervised Process Reward Models
Unsupervised PRMs derived from LLM probabilities achieve up to 15% better error detection than LLM judges and match supervised PRMs in verification and RL tasks.
-
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
DataPRM is a new process reward model for data analysis agents that detects silent errors via environment interaction and ternary rewards, yielding 7-11% gains on benchmarks and further RL improvements.
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
OpenClaw-RL: Train Any Agent Simply by Talking
OpenClaw-RL recovers evaluative and directive signals from next-state interactions to enable online RL training of agents across terminal, GUI, SWE, and tool environments via a server-client architecture and hybrid objective.
-
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
STOP is a new learnable internal path-pruning technique that improves efficiency and accuracy of parallel reasoning in LRMs under fixed compute budgets.