Allen通过步骤级自主性提升多智能体系统协作效率与可控性。
Allen: Rethinking MAS Design through Step-Level Policy Autonomy
- 以步骤为基本单元，实现智能体动态组合策略
- 四层状态架构统一优化拓扑与执行进度
- 适合需要灵活协作与可控监督的复杂任务场景
我们提出一种新型多智能体系统（MAS）Allen，旨在解决当前设计中的两大核心挑战：（1）提升系统的策略自主性，使智能体能够动态调整行为策略；（2）在复杂网络拓扑中实现协作效率、任务监管与人类监督之间的平衡。核心思想是重新定义MAS的基本执行单元，使智能体可通过组合这些单元自主形成不同行为模式。为此构建了四层状态架构（任务、阶段、智能体、步骤），从任务导向和执行导向双重角度约束系统行为，实现了拓扑优化与可控进展的统一。Allen赋予系统前所未有的策略自主性，同时在协作结构的可控性上做出合理权衡。项目代码已开源：https://github.com/motern88/Allen
原文摘要 · Abstract (English)
We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining these units. We have constructed a four-tier state architecture (Task, Stage, Agent, Step) to constrain system behavior from both task-oriented and execution-oriented perspectives. This achieves a unification of topological optimization and controllable progress. Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure. The project code has been open source at: https://github.com/motern88/Allen
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。