Skip to content
NeurIPS 2026 planner

Poster · Sydney

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation

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
zhiqi yu, Zhangquan Chen, Mengting Liu, Heye Zhang, Liangqiong Qu
Organisations
Tsinghua University, Sun Yat-sen University, University of Hong Kong
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page