让多个智能体自我博弈优化，自动找到最佳研究方案。
Self-Optimizing Multi-Agent Systems for Deep Research
- 智能体通过自博弈探索不同提示组合，动态优化研究流程。
- 在复杂信息检索任务中，性能媲美甚至超越人工精心设计的提示。
- 适合需要持续优化的研究系统开发者或自动化研究平台构建者。
当用户提出复杂的知识需求时，多智能体深度研究系统会迭代地规划、检索并整合数百份文档中的证据，以生成高质量的答案。一种可能的架构是：由一个协调智能体统筹全局，多个并行工作智能体执行具体任务。然而，当前的深度研究系统通常依赖手工设计的提示和固定架构，导致改进过程脆弱、成本高且耗时。为此，本文探索多种多智能体优化方法，表明让智能体进行自我对弈并尝试不同的提示组合，能够构建出性能匹配甚至超越专家手工设计提示的高质量研究系统。
原文摘要 · Abstract (English)
Given a user's complex information need, a multi-agent Deep Research system iteratively plans, retrieves, and synthesizes evidence across hundreds of documents to produce a high-quality answer. In one possible architecture, an orchestrator agent coordinates the process, while parallel worker agents execute tasks. Current Deep Research systems, however, often rely on hand-engineered prompts and static architectures, making improvement brittle, expensive, and time-consuming. We therefore explore various multi-agent optimization methods to show that enabling agents to self-play and explore different prompt combinations can produce high-quality Deep Research systems that match or outperform expert-crafted prompts.
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。