works on
language models 1open-ended generation 1policy optimization 1reward modeling 1self-evolving rubrics 1test-time reinforcement learning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CL2026

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning

Jianze Wang, Kunwang Zheng, Ying Liu +5

The paper introduces SERPO, a test-time reinforcement learning approach that lets language models self‑improve during inference by jointly evolving response evidence, query‑specifi…