Process Reinforcement Through Implicit Rewards
Release time:2026-08-26
Hits:
- Journal:
- Transactions on Machine Learning Research (TMLR), 2026.
- Abstract:
- Ganqu Cui, Lifan Yuan, Zefan Wang, Bowen Zhou†, Ning Ding, et al
- Note:
- RL Theory Process-level reinforcement learning with implicit reward shaping for reasoning
- Translation or Not:
- no
- Links to published journals:
- https://arxiv.org/abs/2502.01456