SIGMAS: Second-Order Interaction-based Grouping for Overlapping Multi-Agent Swarms

TL;DR

This paper introduces SIGMAS, a self-supervised method for inferring overlapping group structures in multi-agent swarms by modeling second-order interactions, advancing understanding of complex swarm behaviors.

Contribution

The paper presents a novel second-order interaction-based framework for group prediction in overlapping swarms, without requiring ground-truth labels, and demonstrates its effectiveness across synthetic scenarios.

Findings

Accurately recovers latent group structures in synthetic swarms.

Robustly handles overlapping and dynamic swarm scenarios.

Establishes a new benchmark task for swarm group inference.

Abstract

Swarming systems, such as drone fleets and robotic teams, exhibit complex dynamics driven by both individual behaviors and emergent group-level interactions. Unlike traditional multi-agent domains such as pedestrian crowds or traffic systems, swarms typically consist of a few large groups with inherent and persistent memberships, making group identification essential for understanding fine-grained behavior. We introduce the novel task of group prediction in overlapping multi-agent swarms, where latent group structures must be inferred directly from agent trajectories without ground-truth supervision. To address this challenge, we propose SIGMAS (Second-order Interaction-based Grouping for Multi-Agent Swarms), a self-supervised framework that goes beyond direct pairwise interactions and model second-order interaction across agents. By capturing how similarly agents interact with others, SIGMAS enables robust group inference and adaptively balances individual and collective dynamics through a learnable gating mechanism for joint reasoning. Experiments across diverse synthetic swarm scenarios demonstrate that SIGMAS accurately recovers latent group structures and remains robust under simultaneously overlapping swarm dynamics, establishing both a new benchmark task and a principled modeling framework for swarm understanding.