Papers
arxiv:2508.03923

CoAct-1: Computer-using Agents with Coding as Actions

Published on Aug 5
· Submitted by linxinso on Aug 8
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

A multi-agent system that combines GUI control with programmatic execution improves efficiency and success in complex computer automation tasks.

AI-generated summary

Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they remain constrained by the inherent limitations of performing all actions through GUI manipulation, leading to brittleness and inefficiency. In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as a enhanced action. We present CoAct-1, a novel multi-agent system that synergistically combines GUI-based control with direct programmatic execution. CoAct-1 features an Orchestrator that dynamically delegates subtasks to either a conventional GUI Operator or a specialized Programmer agent, which can write and execute Python or Bash scripts. This hybrid approach allows the agent to bypass inefficient GUI action sequences for tasks like file management and data processing, while still leveraging visual interaction when necessary. We evaluate our system on the challenging OSWorld benchmark, where CoAct-1 achieves a new state-of-the-art success rate of 60.76%, significantly outperforming prior methods. Furthermore, our approach dramatically improves efficiency, reducing the average number of steps required to complete a task to just 10.15, compared to 15 for leading GUI agents. Our results demonstrate that integrating coding as a core action provides a more powerful, efficient, and scalable path toward generalized computer automation.

Community

Typo: enabling agents to use coding as a enhanced action -> enabling agents to use coding as an enhanced action

Paper author Paper submitter
  • New SOTA on OSWorld, 60.8% success rate & 11.1 steps/task
  • Multi-agent architecture
  • Redefines efficiency, code-writing (Python/Bash) + GUI operations

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.03923 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.03923 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.03923 in a Space README.md to link it from this page.

Collections including this paper 1