CoworkEnv synthesizes executable training environments for long-horizon cowork agents
Zhongwei Xie · hf · 2026-10-20
Researchers from HKUST, CUHK and HKBU present CoworkEnv, a capability-guided framework that synthesizes executable training environments for AI coworkers. Workflow requirements guide task construction; programmatic validation with feedback-repair checks generates specs and grading. Teacher executions yield curated demonstrations for SFT while the environments also support RL, training compact PocketWorker models that improve multi-turn coordination and tool use. Code, models and lessons are open-sourced.
More from coding & agent
- Indie dev says AI removed the model bottleneck: solo-building a physics excavator sim — Michael_J_Black · 2026-10-20
- HSPR Recovers Full Agent Benchmark Scores From Small Subsets via Hierarchical Posterior Inference — SUDA · 2026-10-20
- AdaExploreBench Finds LLM Agents Struggle at Proactive Exploration in Evolving Environments — HKUST · 2026-10-20
- Our OAuth discovery doc and Python docs give agents opposite signup instructions — bshivarthy · 2026-10-20
- Fo launches MCP to let AI agents control and sense physical devices, 100+ devs already building — heyshrutimishra · 2026-10-20
- Open-source humanoid Asimov 1 ships docs: assembly guides, sim-to-real training, browser demo — Sentdex · 2026-10-20