CoAct-1: Computer-using Multi-Agent System with Coding Actions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Song, Linxin, Dai, Yutong, Prabhu, Viraj, Zhang, Jieyu, Shi, Taiwei, Li, Li, Li, Junnan, Savarese, Silvio, Chen, Zeyuan, Zhao, Jieyu, Xu, Ran, Xiong, Caiming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915808364462080
author Song, Linxin
Dai, Yutong
Prabhu, Viraj
Zhang, Jieyu
Shi, Taiwei
Li, Li
Li, Junnan
Savarese, Silvio
Chen, Zeyuan
Zhao, Jieyu
Xu, Ran
Xiong, Caiming
author_facet Song, Linxin
Dai, Yutong
Prabhu, Viraj
Zhang, Jieyu
Shi, Taiwei
Li, Li
Li, Junnan
Savarese, Silvio
Chen, Zeyuan
Zhao, Jieyu
Xu, Ran
Xiong, Caiming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoAct-1: Computer-using Multi-Agent System with Coding Actions
Song, Linxin
Dai, Yutong
Prabhu, Viraj
Zhang, Jieyu
Shi, Taiwei
Li, Li
Li, Junnan
Savarese, Silvio
Chen, Zeyuan
Zhao, Jieyu
Xu, Ran
Xiong, Caiming
Computation and Language
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.
title CoAct-1: Computer-using Multi-Agent System with Coding Actions
topic Computation and Language
url https://arxiv.org/abs/2508.03923