About

Hi! I’m Haojun Shi. I am currently a first year PhD student at Yale majoring in Computer Science, advised by Prof. Arman Cohan. Prior to joining Yale, I was an undergraduate at Johns Hopkins advised by Prof. Tianmin Shu and Prof. Jason Eisner.

News

  • [Nov 2025] — Our paper “RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users” is accepted to AAAI 2026!
  • [Oct 2025] — Our paper “RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users” is accepted to NeurIPS 2025 workshops SEA (Scaling Environments for Agents), MTI (Multi-Turn Interactions in Large Language Models), and LAW (Bridging Language, Agent, and World Models for Reasoning and Planning)!
  • [Jan 2025] — Our paper “MuMA-ToM: Multi-modal Multi-Agent Theory of Mind” is accepted to AAAI 2025 with Oral Presentation!

Publications

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

Haojun Shi*, Suyu Ye*, Xinyu Fang, Chuanyang Jin, Leyla Isik, Yen-Ling Kuo, Tianmin Shu  (* equal contribution)
AAAI 2025 (Oral)
Paper · Website · Code

MuMA-ToM

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users

Suyu Ye*, Haojun Shi*, Darren Shih, Hyokun Yun, Tanya Roosta, Tianmin Shu  (* equal contribution)
AAAI 2026
Paper · Website · Code

RealWebAssist

© 2026 Haojun Shi. All rights reserved.

Powered by Hydejack v9.2.1