Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration

TL;DR

This paper investigates how heterogeneity and complex task structures in multi-agent ad-hoc collaboration lead to systemic inefficiencies, bottlenecks, and inequality, using an agent-based kitchen environment model.

Contribution

It introduces a model that combines diverse agent traits with complex tasks to analyze emergent inefficiencies and proposes insights for designing effective multi-agent teamwork.

Findings

Rigid role assertion causes bottlenecks and workload inequality.

Team size and communication overhead impact collaboration efficiency.

Micro-level behaviors influence macro-level systemic outcomes.

Abstract

Computational models of collaboration without prior coordination often overlook how heterogeneous agent traits and complex task structures jointly produce systemic bottlenecks, inefficiencies, and contribution inequalities. We address this by using an agent-based model of ad-hoc teamwork in a kitchen environment. Our model integrates diverse agent personas with tasks that combine serial and parallel dependencies. We identify a specialist's dilemma, where rigid role assertion generates system-level bottlenecks, amplifies workload inequality, and fosters fragmented, homophilous networks. We also find that team size and communication overhead interact with problem structure to generate diminishing returns and redundant collaboration. Linking micro-level behavior to macro-level outcomes provides insights into emergent collaboration and design principles for effective multi-agent teamwork.