MinionsLLM: 自然言語によるマルチエージェントシステムの訓練と制御のためのタスク適応型フレームワーク
MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language
LLMとビヘイビアツリー・形式文法を組み合わせ、自然言語でマルチエージェントを制御する枠組みを提案。合成データで微調整し、小規模モデルでもタスク性能が最大33%向上することを示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Andres Garcia Rincon, Eliseo Ferrante
分類: cs.CL, cs.AI, cs.LG, cs.MA, cs.RO
原文アブストラクト
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.
