OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

TL;DR

OS-Symphony introduces a comprehensive framework that enhances the robustness and generalization of computer-using agents through long-term memory and visual-aware tutorial retrieval, achieving state-of-the-art results.

Contribution

The paper presents OS-Symphony, a holistic framework combining a reflection-memory agent and versatile tool agents with multimodal search, addressing robustness and generalization in CUAs.

Findings

Achieves 65.84% on OSWorld benchmark.

Significant performance improvements across various model scales.

Sets new state-of-the-art results on three online benchmarks.

Abstract

While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of granular control over historical visual context curation and the absence of visual-aware tutorial retrieval. To bridge these gaps, we introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation: (1) a Reflection-Memory Agent that utilizes milestone-driven long-term memory to enable trajectory-level self-correction, effectively mitigating visual context loss in long-horizon tasks; (2) Versatile Tool Agents featuring a Multimodal Searcher that adopts a SeeAct paradigm to navigate a browser-based sandbox to synthesize live, visually aligned tutorials, thereby resolving fidelity issues in unseen scenarios. Experimental results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales, establishing new state-of-the-art results on three online benchmarks, notably achieving 65.84% on OSWorld.