Skip to content

Author

Xiaojun Quan

We have 2 of 12 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Stabilizing Policy Optimization via Logits Convexity

This work investigates the stability gap between SFT and RL from a gradient-based perspective, and shows that the convexity of the SFT loss with respect to model logits plays a key role in enabling stable training.

Hongzhan Chen, Tao Yang, Yu-Hua Zhu et al. · 0 citations
Preprint Aug 2026

Cross-Domain Hybrid OPD for Generalizable Search Agents

This technical report presents the training framework behind the Yuanbao search agent, designed to achieve search specialization without sacrificing general intelligence, and combines agentic reinforcement learning for autonomous search with a cross-domain expert On-Policy Distillation pipeline.

Hongzhan Chen, Xiaoyu Liu, Dengming Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.