RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning

arXiv:2610.17623v1 Announce Type: cross Abstract: Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carries and gives no GRPO reward gradient when a grou

← Back to all developments · Signals are a development reported by more than one source. See the methodology.