Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

ArXi:2603.09803v1 Announce Type: new Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better reasoning are better teachers: high-quality solutions serve as effective nstrations than low-quality ones. We term this teaching ability nstration Utility, and show that the policy model's own in-context learning ability provides an efficient way to measure it, yielding a quality signal termed Evidence Gain.