SERL: Self-Examining Reinforcement Learning on Open-Domain

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable rewards as required by Reinforcement Learning with Verifiable Rewards (RLVR); (2) Reinforcement Learning from Human Feedback (RLHF) relies on external reward mechanisms. To overcome these limitations, we propose Self-Examining Reinforcement Learning (SERL), a novel self-improving framework where the LLM serves as both Actor and Judge. SERL introduces two synergistic reward mechanisms without any external signals. On the one hand, to improve the Actor's capability, we derive rewards from Copeland-style pairwise comparison judgments across a group of generated responses. On the other hand, a self-consistency reward that encourages coherent judgments is proposed to improve the Judge's reliability. This refinement strengthens the Judge, consequently generating a more robust training signal for the Actor. Experiments show that our method outperforms existing self-improvement training methods. SERL improves the LC win rate of Qwen3-8B on AlpacaEval 2.0 from 52.37% to 59.90%. To the best of our knowledge, our method achieves state-of-the-art performance among self-improving approaches. Furthermore, it achieves a performance comparable to significantly larger models like Qwen3-32B, demonstrating superior effectiveness and robustness on open-domain tasks.

Authors

• Weixuan Ou Zhejiang University
• Yanzhao Zheng Alibaba Group
• Shuoshuo Sun Alibaba Group
• Wei Zhang
• Baohua Dong Alibaba Group
• Hangcheng Zhu Alibaba Group
• Ruohui Huang Alibaba Group
• Gang Yu Tencent PCG, China
• Pengwei Yan Department of Information Resources Management, Zhejiang University, Hangzhou, 310058, China Alibaba Group, Hangzhou, 311121, China
• Yifan Qiao National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University

Keywords

No keywords are indexed for this paper.