Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Papers with Code Trending Papers

Summary

Agent S2 is a new compositional framework for computer use agents that achieves state-of-the-art performance on multiple benchmarks by utilizing Mixture-of-Grounding and Proactive Hierarchical Planning.

Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant challenges: imprecise grounding of GUI elements, difficulties with long-horizon task planning, and performance bottlenecks from relying on single generalist models for diverse cognitive tasks. To this end, we introduce Agent S2, a novel compositional framework that delegates cognitive responsibilities across various generalist and specialist models. We propose a novel Mixture-of-Grounding technique to achieve precise GUI localization and introduce Proactive Hierarchical Planning, dynamically refining action plans at multiple temporal scales in response to evolving observations. Evaluations demonstrate that Agent S2 establishes new state-of-the-art (SOTA) performance on three prominent computer use benchmarks. Specifically, Agent S2 achieves 18.9% and 32.7% relative improvements over leading baseline agents such as Claude Computer Use and UI-TARS on the OSWorld 15-step and 50-step evaluation. Moreover, Agent S2 generalizes effectively to other operating systems and applications, surpassing previous best methods by 52.8% on WindowsAgentArena and by 16.52% on AndroidWorld relatively. Code available at https://github.com/simular-ai/Agent-S.
Original Article
View Cached Full Text

Cached at: 05/08/26, 09:02 AM

Paper page - Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Source: https://huggingface.co/papers/2504.00906

Abstract

Agent S2, a compositional framework using Mixture-of-Grounding and Proactive Hierarchical Planning, achieves state-of-the-art performance in computer use automation across various benchmarks and operating systems.

Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant challenges: imprecise grounding of GUI elements, difficulties with long-horizon task planning, and performance bottlenecks from relying on single generalist models for diverse cognitive tasks. To this end, we introduce Agent S2, a novelcompositional frameworkthat delegates cognitive responsibilities across various generalist and specialist models. We propose a novelMixture-of-Groundingtechnique to achieve precise GUI localization and introduceProactive Hierarchical Planning, dynamically refining action plans at multiple temporal scales in response to evolving observations. Evaluations demonstrate that Agent S2 establishes new state-of-the-art (SOTA) performance on three prominent computer use benchmarks. Specifically, Agent S2 achieves 18.9% and 32.7% relative improvements over leading baseline agents such as Claude Computer Use and UI-TARS on the OSWorld 15-step and 50-step evaluation. Moreover, Agent S2 generalizes effectively to other operating systems and applications, surpassing previous best methods by 52.8% on WindowsAgentArena and by 16.52% on AndroidWorld relatively. Code available at https://github.com/simular-ai/Agent-S.

View arXiv pageView PDFProject pageGitHub11.2kAdd to collection

Get this paper in your agent:

hf papers read 2504\.00906

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2504.00906 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2504.00906 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2504.00906 in a Space README.md to link it from this page.

Collections including this paper12

Browse 12 collections that include this paper

Similar Articles

AgentOS

Product Hunt

AgentOS provides a unified control layer for managing AI agents, tasks, and workspaces.

AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows

arXiv cs.AI

AgentCo-op is a retrieval-based synthesis framework for composing interoperable multi-agent workflows from reusable skills, tools, and external agents. It uses typed artifact handoffs and bounded self-guided local repair, achieving strong results on benchmarks and enabling collaborative discovery in open-world genomics tasks.