IFS: Information Flow Structure for Multi-agent Ad Hoc System

TL;DR

This paper introduces IFS, a novel information flow structure for multi-agent ad hoc systems that enhances communication and information processing, leading to improved teamwork performance in dynamic, uncertain environments.

Contribution

The paper proposes IFS, a new framework addressing information flow limitations in multi-agent ad hoc systems, with demonstrated effectiveness in complex scenarios.

Findings

IFS significantly improves information flow and processing capacity.

IFS outperforms baseline methods in StarCraft II teamwork tasks.

IFS exhibits strong generalization capabilities.

Abstract

Multi-agent ad hoc systems are dynamic collaborative systems in which multiple autonomous agents must cooperate with both known and unknown teammates in open environments, without relying on pre-coordinated strategies. These systems operate under conditions of uncertainty and partial observability, where team composition, agent behaviors, and environmental factors may change during execution. Through an analysis of information flow in such systems, we identify two key limitations in existing research: insufficient information flow and limited information processing capacity. To address these issues, we propose an information flow structure for multi-agent ad hoc systems (IFS), which tackles these challenges from the perspectives of communication and information fusion. Experimental results in StarCraft II demonstrate that IFS significantly improves both information flow and processing capacity, while exhibiting strong generalization capabilities and outperforming baseline methods in complex ad hoc teamwork scenarios.