LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS

TL;DR

AIOS 1.0 transforms computers into environment models for language models, enabling more effective computer-use agents like LiteCUA, which outperforms some specialized frameworks on the OSWorld benchmark.

Contribution

We introduce AIOS 1.0 with a Model Context Protocol server architecture that bridges language understanding and computer interfaces, and demonstrate a lightweight agent, LiteCUA, that benefits from this approach.

Findings

LiteCUA achieves 14.66% success on OSWorld benchmark.

AIOS 1.0 effectively decouples interface and decision complexity.

Contextualized environments improve agent reasoning capabilities.

Abstract

We present AIOS 1.0, a novel platform designed to advance computer-use agent (CUA) capabilities through environmental contextualization. While existing approaches primarily focus on building more powerful agent frameworks or enhancing agent models, we identify a fundamental limitation: the semantic disconnect between how language models understand the world and how computer interfaces are structured. AIOS 1.0 addresses this challenge by transforming computers into contextual environments that language models can natively comprehend, implementing a Model Context Protocol (MCP) server architecture to abstract computer states and actions. This approach effectively decouples interface complexity from decision complexity, enabling agents to reason more effectively about computing environments. To demonstrate our platform's effectiveness, we introduce LiteCUA, a lightweight computer-use agent built on AIOS 1.0 that achieves a 14.66% success rate on the OSWorld benchmark, outperforming several specialized agent frameworks despite its simple architecture. Our results suggest that contextualizing computer environments for language models represents a promising direction for developing more capable computer-use agents and advancing toward AI that can interact with digital systems.