让多个智能体在复杂任务中高效协作，通过动态监控优化全局表现。
Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
- 基于注意力机制的自组织协作与反思性评估
- 在渐进复杂的迷宫任务中显著提升协调效率
- 适合长期目标、动态环境下的多智能体系统
复杂非线性任务对增强大语言模型的多智能体系统（MAS）构成挑战，主要源于部分可观测性与协作不佳。本文提出 Orchestrator，一种新型多智能体框架，通过受注意力启发的自涌现协调机制与反思性基准评估，优化整体任务性能。该框架引入监控机制，追踪智能体-环境动态，利用主动推理基准优化系统行为。通过监测智能体间及智能体与环境间的交互，有效缓解部分可观测性问题，使智能体更高效地逼近全局任务解。我们在一系列复杂度递增的迷宫谜题上评估该框架，验证其在具有长期目标的动态非线性环境中提升协作与性能的有效性。
原文摘要 · Abstract (English)
Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination and reflective benchmarking to optimize global task performance. Orchestrator introduces a monitoring mechanism to track agent-environment dynamics, using active inference benchmarks to optimize system behavior. By tracking agent-to-agent and agent-to-environment interaction, Orchestrator mitigates the effects of partial observability and enables agents to approximate global task solutions more efficiently. We evaluate the framework on a series of maze puzzles of increasing complexity, demonstrating its effectiveness in enhancing coordination and performance in dynamic, non-linear environments with long-horizon objectives.
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。