Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured framework that explores the same space through a fixed set of simple, composable components. We show that, despite lacking the generative flexibility of LLMs during the candidate generation stage, our method outperforms prior approaches on four out of five benchmarks across two domains: mathematics and question answering. Furthermore, our method offers additional advantages, including a more cost-efficient search process and the generation of modular, interpretable multi-agent systems with simpler logic.

翻译：多智能体系统的自动搜索近年来已成为智能体人工智能研究的关键焦点。先前的一些方法依赖于基于大型语言模型（LLM）在代码空间中进行自由形式搜索。在本研究中，我们提出了一种更具结构化的框架，通过一组固定的、可组合的简单组件来探索同一空间。我们证明，尽管在候选生成阶段缺乏LLM的生成灵活性，但我们的方法在数学和问答两个领域的五个基准测试中的四个上优于先前的方法。此外，我们的方法还提供了额外优势，包括更经济高效的搜索过程，以及生成具有更简单逻辑的模块化、可解释的多智能体系统。