Self-play supports the self-evolution of language models, but solver performance can plateau or decline across rounds without guidance. Existing unguided methods typically use difficulty, learnability, or diversity signals to keep questions challenging and varied, without identifying which unresolved reasoning weakness...
Xin Wei, Yinze Ding, Fu-Cheng Xiong et al.· 1 citation
On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard OPSD uses one fixed parameter setting at every state, but nearby settings may offer additional supervision. We find that local parameter per...
Xin Wei, Yi-Fan Ding, Yoshua Y. Li et al.· 0 citations
A critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process and improves the actor’s exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger actor model.
Zhi-Heng Xi, Dingwen Yang, Jixuan Huang et al.· Proceedings of the Thirty-Fi...· 0 citations
SA is proposed, a Stable Advantage Fusion framework that avoids entropy collapse and consistently outperforms fixed-coefficient GRPO+OPD fusion, improving the aggregate score by 0.70% across all six model-domain settings while achieving more stable training.
Yifan Ding, Xin Wei, Yoshua Y. Li et al.· arXiv.org· 3 citations
DagEvo is introduced, whose diagnostician extracts recurring error causes from this history and stores them in a hierarchical error-cause memory, whose diagnostician extracts recurring error causes from this history and stores them in a hierarchical error-cause memory.
Xin Wei, Yinze Ding, Yoshua Y. Li et al.· 0 citations
This work eliminates external gold supervision from the RL training reward: the model's own evaluative capability generates learning signals for its optimization -- a closed-loop setting of bounded recursive self-improvement (RSI) termed Recursive Self-Evaluation (RecurSE).
Kai-Yuan Liu, Ziyuan Zhuang, Rong-Xiang Weng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
