Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation

The paper introduces CoCA, a closed‑loop framework that jointly evolves a policy and its rubric by diagnosing each rubric criterion against the current policy’s capabilities. CoCA contrasts query‑only and rubric‑guided rollouts to identify mismatched difficulty, recalibrates criteria, and uses frontier‑based learning or self‑distillation to align the rubric with the policy’s evolving strengths. Experiments on various benchmarks and large language models show that CoCA consistently outperforms existing rubric‑based reinforcement learning methods and helps the policy internalize guidance‑revealed capabilities while preventing degradation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• reinforcement-learning
• efficiency
• benchmarks