Skip to content
View ProKil's full-sized avatar
🎯
Focusing
🎯
Focusing
385 followers · 81 following

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: YOLOAchievement: Starstruckx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: YOLOAchievement: Starstruckx3Achievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@SALT-NLP @sotopia-lab @Open-Social-World @cooperbench

Block or report ProKil

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ProKil/README.md

Hao Zhu

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.

🌐 hao.computer · 🎓 Google Scholar · 🦋 Bluesky · 𝕏 @_Hao_Zhu

Selected projects

Sotopia — Open-ended social learning environment for language agents. ICLR 2024 Spotlight.

CooperBench — Why frontier coding agents lose ~50% of their solo performance when forced to collaborate. ICLR 2026 MAL-GAI Workshop Oral.

AutoLibra — Turning open-ended human feedback into reliable agent metrics. ICLR 2026.

WebArena — 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 — Lightweight Python actor-model library powering asynchronous multi-agent systems.

Pinned Loading

  1. sotopia-lab/sotopia sotopia-lab/sotopia Public

    Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

    Python 300 42

  2. cooperbench/CooperBench cooperbench/CooperBench Public

    A benchmark for evaluating how well AI coding agents can cooperate on software engineering tasks with potential conflicts.

    Python 12 8

  3. Open-Social-World/autolibra Open-Social-World/autolibra Public

    AutoLibra: Metric Induction for Agents from Open-Ended Human Feedback

    Python 19 2

  4. thunlp/FewRel thunlp/FewRel Public

    A Large-Scale Few-Shot Relation Extraction Dataset

    Python 746 161

  5. aact aact Public

    AAct -- An actor model library in Python

    Python 9

  6. sotopia-lab/awesome-social-agents sotopia-lab/awesome-social-agents Public

    A collection of works that investigate social agents, simulations and their real-world impact in text, embodied, and robotics contexts.

    TypeScript 112 25