Grammar Search for Multi-Agent Systems
Mayank Singh University of Arizona, Vikas Yadav, Shiva Krishna Reddy Malay ServiceNow Inc, Shravan Nayak Université de Montréal, Sai Rajeswar, Sathwik Tejaswi Madhusudhan Cartesia, Eduardo Blanco University of Arizona
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 composable components. We show that, despite lacking the generative flexibility of LLMs during the candidate generation stage, our method outperforms prior approaches on a majority of evaluated benchmarks across two backbone LLMs and 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.
尚无 AI 解读，展示原文摘要
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表