A new multi-turn reinforcement learning framework trains a single LLM to both solve math problems and verify its own solutions, revising only when its verifier finds a mistake.
Rm-r1: Reward modeling as reasoning, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
A new multi-turn reinforcement learning framework trains a single LLM to both solve math problems and verify its own solutions, revising only when its verifier finds a mistake.