SiriuS：通过自举推理实现自我改进的多智能体系统
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
AI总结：
SiriuS提出一种通过构建高质量推理轨迹经验库并增强失败轨迹来实现多智能体系统自我改进的框架，在推理、生物医学问答和协商任务上取得显著性能提升。
摘要：
由大型语言模型（LLMs）驱动的多智能体AI系统越来越多地被用于解决复杂任务。然而，这些系统通常依赖脆弱且手工设计的提示和启发式规则，使得优化变得困难。优化多智能体系统的一个关键挑战在于为专用智能体获取合适的训练数据。我们提出了SiriuS，一个面向多智能体系统的自我改进、推理驱动的优化框架。该方法的核心是构建一个经验库：一个高质量推理轨迹的存储库。该库通过保留能够带来成功结果的推理步骤来构建，从而为优化多智能体系统提供稳健的训练集。此外，我们引入了一种库增强过程，用于精炼不成功的轨迹，进一步丰富经验库。SiriuS在推理和生物医学问答任务上将性能提升了2.86%至21.88%，并在竞争性环境中增强了智能体协商能力。我们的结果表明，SiriuS在提升多智能体性能的同时，生成了可用于未来自我纠正和自我博弈增强的可复用数据。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
