通过自生成推理轨迹库，让多智能体系统自我优化。
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
- 构建高质量推理轨迹库，自动筛选成功路径
- 性能提升2.86%至21.88%，增强谈判能力
- 适合需要持续优化的复杂任务系统
由大语言模型驱动的多智能体系统在解决复杂任务中日益普及。然而，这些系统通常依赖脆弱的手动设计提示和启发式规则，导致优化困难。多智能体系统优化的关键挑战在于获取特定智能体的优质训练数据。本文提出SiriuS，一种基于推理驱动的自改进多智能体系统优化框架。核心是构建经验库：一个保存成功推理轨迹的高质数据仓库。该库通过保留导向成功结果的推理步骤生成，为智能体优化提供稳健训练集。此外，我们引入库增强机制，对失败轨迹进行精炼，进一步丰富库内容。SiriuS在推理与生物医学问答任务上性能提升2.86%至21.88%，并增强了竞争场景下的智能体协商能力。结果表明，SiriuS不仅能提升多智能体表现，还能生成可复用数据，支持未来自纠错与自对弈增强。
原文摘要 · Abstract (English)
Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization difficult. A key challenge in optimizing multi-agent systems is acquiring suitable training data for specialized agents. We introduce SiriuS, a self-improving, reasoning-driven optimization framework for multi-agent systems. Central to our approach is the construction of an experience library: a repository of high-quality reasoning trajectories. The library is built by retaining reasoning steps that lead to successful outcomes, providing a robust training set for optimizing multi-agent system. Additionally, we introduce a library augmentation procedure that refines unsuccessful trajectories, further enriching the library. SiriuS boosts performance by 2.86\% to 21.88\% on reasoning and biomedical QA and enhances agent negotiation in competitive settings. Our results show that SiriuS enhances multi-agent performance while generating reusable data for self-correction and self-play enhancement in the future.
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。