让多个AI代理在不依赖中心服务器的情况下协同工作，提升效率与可靠性。
Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence
- 采用去中心化账本记录各代理能力，实现自主协作。
- 动态任务分配机制使系统在不同模型性能下仍保持高准确率。
- 适合资源有限但需大规模智能协同的场景，如边缘计算。
现有基于大语言模型（LLM）的代理框架多依赖中心化调度，导致部署成本高、通信结构僵化且适应性差。为此，我们提出Symphony——一种去中心化的多代理系统，支持在消费级GPU上运行轻量级LLM进行协同。该系统引入三项核心机制：(1) 去中心化账本记录各代理能力；(2) Beacon选择协议实现动态任务分配；(3) 基于思维链（CoTs）的加权结果投票。该设计实现了低开销、隐私保护、可扩展且容错的协同架构。实验表明，Symphony在推理基准测试中优于现有基线，显著提升准确率，并在不同容量模型间表现出强鲁棒性。
原文摘要 · Abstract (English)
Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce Symphony, a decentralized multi-agent system which enables lightweight LLMs on consumer-grade GPUs to coordinate. Symphony introduces three key mechanisms: (1) a decentralized ledger that records capabilities, (2) a Beacon-selection protocol for dynamic task allocation, and (3) weighted result voting based on CoTs. This design forms a privacy-saving, scalable, and fault-tolerant orchestration with low overhead. Empirically, Symphony outperforms existing baselines on reasoning benchmarks, achieving substantial accuracy gains and demonstrating robustness across models of varying capacities.
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。