Poster · Sydney
ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Sining Zhoubian, Dan Zhang, Jie Tang
- Organisations
- Tsinghua University
- QRS classification
- Reinforcement learning, Language models