Haolong Yan

MS student, Beijing University of Posts and Telecommunications

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

#415 · Haolong Yan, Yeqing Shen, Xin Huang, Jia Wang, Kaijun Tan, Zhixuan Liang, Hongxin Li, Zheng Ge, Osamu Yoshie, Si Li, Xiangyu Zhang, Daxin Jiang

We introduce GUI Exploration Lab, a flexible simulator for GUI agent navigation. Experiments show a staged SFT + RL approach (especially multi-turn RL) significantly boosts navigation and exploration capabilities.