Skip to content
NeurIPS 2026 planner

Poster · Sydney

Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards

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
Jun Nie, Bo Han, Jiaqi Fan, Yonggang Zhang, Xinmei Tian, Dahai Yu, Michael Ng
Organisations
University of Science and Technology of China, Hong Kong Baptist University, RIKEN, TCL Coporate Research, Hong Kong University of Science and Technology, TCL Corporate Research
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page