让多智能体系统在预算内高效协作，成本降86%仍保持性能
BAMAS: Structuring Budget-Aware Multi-Agent Systems
- 通过整数规划选最优模型组合，平衡性能与成本
- 用强化学习确定智能体间协作拓扑结构
- 适合需控制推理成本的复杂任务部署场景
基于大语言模型的多智能体系统已成为解决复杂任务的有力范式。随着系统复杂度提升，成本成为实际部署的关键考量。然而现有工作很少考虑在明确预算约束下如何构建多智能体系统。本文提出BAMAS，一种具有预算意识的多智能体系统构建方法。BAMAS首先通过求解整数线性规划问题，选出性能与成本平衡的最优LLM集合；随后利用基于强化学习的方法，确定这些LLM之间的协作拓扑结构；最后依据选定的智能体及其交互关系进行系统实例化与执行。我们在三个代表性任务上评估BAMAS，与现有先进方法对比，结果表明其在保持相当性能的同时，成本最高可降低86%。
原文摘要 · Abstract (English)
Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks. As these systems scale in complexity, cost becomes an important consideration for practical deployment. However, existing work rarely addresses how to structure multi-agent systems under explicit budget constraints. In this paper, we propose BAMAS, a novel approach for building multi-agent systems with budget awareness. BAMAS first selects an optimal set of LLMs by formulating and solving an Integer Linear Programming problem that balances performance and cost. It then determines how these LLMs should collaborate by leveraging a reinforcement learning-based method to select the interaction topology. Finally, the system is instantiated and executed based on the selected agents and their collaboration topology. We evaluate BAMAS on three representative tasks and compare it with state-of-the-art agent construction methods. Results show that BAMAS achieves comparable performance while reducing cost by up to 86%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。