Skip to content
NeurIPS 2026 planner

Poster · Sydney

Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement Learning

When
Thu 10 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 5
Authors
Renting Rui, Yulei Qin, Weiwen Liu, Yunjia Xi, Ke Li, Xing Sun, Weinan Zhang, Yong Yu
Organisations
Shanghai Jiao Tong University, Tencent
QRS classification
Reinforcement learning, Agentic AI

Open in scheduleOfficial page