Agent S: An Open Agentic Framework that Uses Computers Like a Human

TL;DR

Agent S is a novel open framework that automates complex human-computer interactions using hierarchical planning and multimodal language models, significantly improving success rates on benchmark tasks.

Contribution

It introduces experience-augmented hierarchical planning and an Agent-Computer Interface for GUI automation, advancing the state-of-the-art in autonomous human-computer interaction.

Findings

Outperforms baseline by 9.37% on OSWorld benchmark

Achieves 83.6% success rate, a significant improvement

Demonstrates broad generalizability to different OS environments

Abstract

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facilitating efficient task planning and subtask execution. In addition, it employs an Agent-Computer Interface (ACI) to better elicit the reasoning and control capabilities of GUI agents based on Multimodal Large Language Models (MLLMs). Evaluation on the OSWorld benchmark shows that Agent S outperforms the baseline by 9.37% on success rate (an 83.6% relative improvement) and achieves a new state-of-the-art. Comprehensive analysis highlights the effectiveness of individual components and provides insights for future improvements. Furthermore, Agent S demonstrates broad generalizability to different operating systems on a newly-released WindowsAgentArena benchmark. Code available at https://github.com/simular-ai/Agent-S.