{"ID":2887967,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08283","arxiv_id":"2508.08283","title":"MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language","abstract":"This paper presents MinionsLLM, a novel framework that integrates Large Language Models (LLMs) with Behavior Trees (BTs) and Formal Grammars to enable natural language control of multi-agent systems within arbitrary, user-defined environments. MinionsLLM provides standardized interfaces for defining environments, agents, and behavioral primitives, and introduces two synthetic dataset generation methods (Method A and Method B) to fine-tune LLMs for improved syntactic validity and semantic task relevance. We validate our approach using Google's Gemma 3 model family at three parameter scales (1B, 4B, and 12B) and demonstrate substantial gains: Method B increases syntactic validity to 92.6% and achieves a mean task performance improvement of 33% over baseline. Notably, our experiments show that smaller models benefit most from fine-tuning, suggesting promising directions for deploying compact, locally hosted LLMs in resource-constrained multi-agent control scenarios. The framework and all resources are released open-source to support reproducibility and future research.","short_abstract":"This paper presents MinionsLLM, a novel framework that integrates Large Language Models (LLMs) with Behavior Trees (BTs) and Formal Grammars to enable natural language control of multi-agent systems within arbitrary, user-defined environments. MinionsLLM provides standardized interfaces for defining environments, agent...","url_abs":"https://arxiv.org/abs/2508.08283","url_pdf":"https://arxiv.org/pdf/2508.08283v1","authors":"[\"Andres Garcia Rincon\",\"Eliseo Ferrante\"]","published":"2025-08-01T13:10:29Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\",\"cs.MA\",\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}