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.
π hao.computer Β· π Google Scholar Β· π¦ Bluesky Β· π @_Hao_Zhu
Sotopia β Open-ended social learning environment for language agents. ICLR 2024 Spotlight.
CooperBench β Why frontier coding agents lose ~50% of their solo performance when forced to collaborate. ICLR 2026 MAL-GAI Workshop Oral.
AutoLibra β Turning open-ended human feedback into reliable agent metrics. ICLR 2026.
WebArena β 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 β Lightweight Python actor-model library powering asynchronous multi-agent systems.