Ziqin Gong

I am currently a second-year PhD student of AI Thrust at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Jun Wang. I received my Bachelor’s degree in Computer Science and Technology (IEEE Honor Class) at Shanghai Jiao Tong University under the supervision of Prof. Weinan Zhang.

Research interests

○ Agent

Agents extend foundation models from passive generation to goal-directed interaction, where they reason about tasks, acquire relevant evidence, and make decisions under computational, environmental, and perceptual constraints.

Publications on this topic:

ICML 2026	The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei, Jun Wang
arXiv	OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models Jun Wang, Meng Fang, Ziyu Wan, Muning Wen, Jiachen Zhu, Anjie Liu, Ziqin Gong, Yan Song, Lei Chen, Lionel M. Ni, Linyi Yang, Ying Wen, Weinan Zhang

○ Reinforcement Learning

Reinforcement Learning (RL) has become a promising approach to solving many real-world problems, and the development and application of Deep RL algorithms are yet to be fully explored.

Publications on this topic:

DAI 2024	Looking Ahead to Avoid Being Late: Solving Hard-Constrained Traveling Salesman Problem Jingxiao Chen, Ziqin Gong, Lvda Chen, Minghuan Liu, Jun Wang, Yong Yu, and Weinan Zhang
DAI 2023	RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow Zhengbang Zhu, Shenyu Zhang, Yuzheng Zhuang, Yuecheng Liu, Minghuan Liu, Liyuan Mao, Ziqin Gong, Shixiong Kai, Qiang Gu, Bin Wang, Siyuan Cheng, Xinyu Wang, Jianye Hao, Yong Yu Best Student Paper Award