---
title: "Berkeley researchers open-source unified platform for computer-use agents"
url: https://www.parallelquant.com/posts/berkeley-researchers-open-source-unified-platform-for-computer-use-agent-ae8592
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/09/05/uc-berkeley-researchers-release-cua-lite-an-open-platform-unifying-sandboxes-data-evaluation-and-rl-for-computer-use-agents/
published: 2026-09-06T06:11:02.000Z
topics: ["research", "open source"]
publisher: "Parallel Quant"
---

# Berkeley researchers open-source unified platform for computer-use agents

*2026-09-06 · Source: [MarkTechPost](https://www.marktechpost.com/2026/09/05/uc-berkeley-researchers-release-cua-lite-an-open-platform-unifying-sandboxes-data-evaluation-and-rl-for-computer-use-agents/)*

A UC Berkeley-led team released CUA-Lite, an open platform that standardizes the sandboxes, data formats, evaluation, and reinforcement-learning setups used to train and benchmark computer-use agents. It replaces OSWorld's per-task virtual machines with lightweight Docker containers, cutting the per-task footprint from 4.1GB to 0.9GB.

**Why it matters:** Computer-use agent research has been fragmented across incompatible environments and data schemas, making results hard to compare across labs. A shared, lightweight standard could accelerate progress the way common benchmarks did for earlier ML subfields, and the smaller footprint makes large-scale RL training meaningfully cheaper to run.

**Topics:** research, open source

---
Read the original: https://www.marktechpost.com/2026/09/05/uc-berkeley-researchers-release-cua-lite-an-open-platform-unifying-sandboxes-data-evaluation-and-rl-for-computer-use-agents/
Canonical: https://www.parallelquant.com/posts/berkeley-researchers-open-source-unified-platform-for-computer-use-agent-ae8592
Published by Parallel Quant — https://www.parallelquant.com