I work towards generally intelligent partners for humans, building benchmarks and training methods for AI agents that interact with computers, the physical world, and with humans and other agents.
๐ hao.computer ยท ๐ Google Scholar ยท ๐ฆ Bluesky ยท ๐ @_Hao_Zhu
Sotopia โ Open-ended social learning environment for language agents. ICLR 2024 Spotlight.
CooperBench โ Why frontier coding agents lose ~50% of their solo performance when forced to collaborate. COLM 2026
AutoLibra โ Turning open-ended human feedback into reliable agent metrics. ICLR 2026.
WebArena โ Realistic web environment for autonomous agents. I authored browser_env, the environment layer adopted by BrowserGym, AgentLab, VisualWebArena, and HuggingFace OpenEnv. Used in production at OpenAI Operator, Meta, Google DeepMind, ServiceNow. ICLR 2024.
aact โ Lightweight Python actor-model library powering asynchronous multi-agent systems.





