Hello! I am Zijun Gao. I received my B.S. in Mathematics and Computer Science from the University of Illinois Urbana-Champaign in December 2025.

My research interests include Agentic RL and LLM Reasoning. I am currently working on Self-Improving Agents and Agent Harness.

News

  • 2026.01:  One paper on LLM mathematical reasoning was accepted to ICLR 2026!
  • 2025.03:  One project on multi-agent world simulation was presented at CVPR 2025!

Academic Research

Northwestern University – MLL Lab May 2025 – Jan 2026

Multi-Agent Collaborative Training (MAGEN): Developed a multi-turn multi-agent reinforcement learning framework for collaborative LLM and VLM agents, with a focus on environment design, coordinated reasoning, and credit assignment. Advised by Prof. Manling Li.

Arizona State University – ARC Lab Feb 2025 – Dec 2025

Concept-Oriented Reinforcement Learning (CORE): Proposed the CORE framework to bridge concept definitions and mathematical reasoning through reinforcement learning, and achieved consistent improvements on both in-domain and out-of-domain mathematical benchmarks.
Outcome: ICLR 2026. Supervised by Prof. Ben Zhou. [Paper] [Code]

University of California, San Diego Jul 2024 – Jan 2025

Photorealistic World Simulator (SimWorld): Built photorealistic 3D environments for multi-agent interaction. Developed automated asset pipelines using UnrealCV and Blender, and contributed to large-scale dataset generation.
Outcome: CVPR 2025 Demo Track. Supervised by Prof. Zhiting Hu and Prof. Lianhui Qin. [Project Website]

Industry Experience

Meituan – LongCat Post-Training Group May 2026 – Present

Baidu – ERNIE Post-Training Group Apr 2026 – May 2026

Education

University of Illinois Urbana-Champaign (UIUC) Jan 2024 – Dec 2025
B.S. in Mathematics and Computer Science, Highest Distinction

Beijing Jiaotong University (BJTU) Aug 2021 – Dec 2023
B.E. in Computer Science and Technology, Top 5% (Transferred)