English

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

Multiagent Systems 2026-05-12 v1 Human-Computer Interaction

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.

Keywords

Cite

@article{arxiv.2605.08540,
  title  = {Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration},
  author = {Benjamin Panny and Shashank Mehrotra and Zahra Zahedi and Teruhisa Misu and Kumar Akash},
  journal= {arXiv preprint arXiv:2605.08540},
  year   = {2026}
}

Comments

Published in Proceedings of Proc. of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)