Berkeley's CUA-Lite: Open Platform Unifies Eval, SFT & RL for Computer-Use Agents
dawnsongtweets · x · 2026-09-01
Dawn Song's team at Berkeley RDI released CUA-Lite, an open platform for computer-use agents (CUAs) that tackles fragmentation across agents, environments, traces, and training frameworks.
Key pieces:
- One standardized interface and action space between agents and environments, spanning desktop, browser, and mobile
- A unified trace format (LiteSample) — one agent's rollouts can train any other agent via lightweight model adapters
- Lite.Gym connects eval → SFT → RL in one framework, with RL methods like GRPO/GSPO built on Slime
- Optional VM-free Docker sandboxes needing no /dev/kvm, using under ¼ the memory/CPU, with many parallel instances per machine
Already integrated: 10+ CUAs (GPT, Claude, Gemini, Qwen, UI-TARS), 15+ benchmarks (OSWorld, WebArena, AndroidWorld), 30K+ verifiable tasks, and 10+ datasets free on Hugging Face, plus a leaderboard with independently reproduced scores. The project is led by PhD student Zhanhui Zhou and is community-driven open source.
Related event: Berkeley Releases CUA-Lite Open Platform for Computer-Use Agents(2 posts)→
More from coding & agent
- Dev shares a dirt-cheap approach to visual diffs — zeeg · 2026-09-01
- Grok Bot automates Shopify updates and supplier coordination — billyjhowell · 2026-09-01
- Investor calls GrokBot the next ChatGPT moment: 3 minutes beats hours of work — 新智元 · 2026-09-01
- Grok Bot automates lost deal analysis by mining call and email threads — lennysan · 2026-09-01
- Design pattern: immutable agent artifact revisions behind a stable review URL — RocketSeven · 2026-09-01
- Building a long-term memory benchmark for agents: what to add? — True_Mongoose_7073 · 2026-09-01