Grammar Search for Multi-Agent Systems
Published in Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
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.
Recommended citation: Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay, Shravan Nayak, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, and Eduardo Blanco. 2026. Grammar Search for Multi-Agent Systems. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1640–1655, San Diego, California, United States.
Download Paper