Poster · Sydney
Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Ziheng Li, Zexu Sun, Jinman Zhao, Erxue Min, Yongcheng Zeng, Hui Wu, Hengyi Cai, Shuaiqiang Wang, Xu Chen, Zhihong Deng, Dawei Yin
- Organisations
- Peking University, Baidu, University of Toronto, Chinese Academy of Sciences, Renmin University of China
- QRS classification
- Reinforcement learning, Language models