Free Process Rewards without Process Labels

Lifan Yuan, Wendi Li, Huayu Chen, Ganqu Cui, Ning Ding +4 more
2/14/2026

No official code found. Best implementation: PRIME-RL/ImplicitPRM (171 stars, Apache-2.0, last commit 2025-03-14).

Semantic Scholar

Code Implementations(1)

PRIME-RL/ImplicitPRMCommunity61%
Apache-2.0

Repo of paper "Free Process Rewards without Process Labels"

17111Shell, PythonDec 4, 20241 years agoApache-2.0
prmrltest-time-scaling

Cite this paper

@article{yuan2026free,
  title  = {Free Process Rewards without Process Labels},
  author = {Lifan Yuan and Wendi Li and Huayu Chen and Ganqu Cui and Ning Ding and Kaiyan Zhang and Bowen Zhou and Zhiyuan Liu and Hao Peng},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:b046f21838da0517b6ef013f5546710829b83658},
  journal = {ICML 2025 2025}
}

Discussion