让多个AI agents协作更智能：结构与调度同步优化，效率提升43%。
Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
- 从概率角度建模协作，同时学习结构和调度策略。
- 在基准测试中平均性能提升8.42%，用词量减少43.19%。
- 适合需要高效动态协作的复杂任务系统设计者。
随着基于大语言模型的多智能体系统规模扩大，如何平衡结构稳定性与动态适应性愈发困难。现有方法或采用固定结构（限制精细控制），或依赖动态调度（结构隐含且不稳定）。本文提出MACA框架，从概率视角将协作视为结构与调度联合分布的后验推断。该框架学习任务与预算相关的参与和交互结构先验，指导基于策略的调度以逼近后验推断，实现高效且可精细控制的解决方案。在多个基准上，MACA平均性能优于自适应基线8.42%，同时节省43.19%的生成token。进一步分析表明，结构与调度的联合适应能抑制冗余交互，使协作收敛至任务有效执行。
原文摘要 · Abstract (English)
As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.
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。