多智能体系统提升桌面自动化任务成功率
Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration
- 基于有限状态机动态调度智能体协作
- 在OSWorld上达57.07%成功率，50步内完成
- 适合需要高可靠性的复杂自动化场景
桌面自动化中的自主智能体在处理复杂多步骤任务时，因协调不足和质量控制缺失而表现不佳。我们提出Agentic Lybic，一个将整个架构设计为有限状态机（FSM）的新型多智能体系统，实现动态编排。系统包含控制器、管理者、三类工作者（技术员负责代码操作，操作员处理图形界面交互，分析师提供决策支持）以及评估器。核心机制是基于FSM的组件间路由，可根据子任务动态选择最优执行策略，实现灵活性与泛化能力。结合强质量门控，系统支持自适应重规划与错误恢复。在官方OSWorld基准测试中，Agentic Lybic以57.07%的成功率（50步内）达到当前最佳水平，显著优于现有方法。结果表明，具备持续质量控制的结构化多智能体编排，可大幅提升复杂计算环境中桌面自动化的可靠性。
原文摘要 · Abstract (English)
Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce Agentic Lybic, a novel multi-agent system where the entire architecture operates as a finite-state machine (FSM). This core innovation enables dynamic orchestration. Our system comprises four components: a Controller, a Manager, three Workers (Technician for code-based operations, Operator for GUI interactions, and Analyst for decision support), and an Evaluator. The critical mechanism is the FSM-based routing between these components, which provides flexibility and generalization by dynamically selecting the optimal execution strategy for each subtask. This principled orchestration, combined with robust quality gating, enables adaptive replanning and error recovery. Evaluated officially on the OSWorld benchmark, Agentic Lybic achieves a state-of-the-art 57.07% success rate in 50 steps, substantially outperforming existing methods. Results demonstrate that principled multi-agent orchestration with continuous quality control provides superior reliability for generalized desktop automation in complex computing environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。