Allen: Rethinking MAS Design through Step-Level Policy Autonomy

TL;DR

Allen introduces a novel multi-agent system that enhances agent policy autonomy and balances collaboration efficiency with controllability through a new architecture and execution units.

Contribution

The paper proposes a new MAS design with step-level policy autonomy and a four-tier architecture to improve adaptability and control in complex network topologies.

Findings

Enhanced policy autonomy in agents

Unified topological optimization and control

Open-source implementation available

Abstract

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