When should we encourage specialization in multi-agent systems versus train generalists that perform the entire task independently? We propose that specialization largely depends on task parallelizability: the potential for multiple agents to execute task components concurrently. Drawing inspiration from Amdahl's Law in distributed systems, we present a closed-form bound that predicts when specialization improves performance, depending only on task concurrency and team size. We validate our model on two standard MARL benchmarks that represent opposite regimes -- StarCraft Multi-Agent Challenge (SMAC, unlimited concurrency) and Multi-Particle Environment (MPE, unit-capacity bottlenecks) -- and observe close alignment between the bound at each extreme and an empirical measure of specialization. Three follow-up experiments in Overcooked-AI demonstrate that the model works in environments with more complex spatial and resource bottlenecks that allow for a range of strategies. Beyond prediction, the bound also serves as a diagnostic tool, highlighting biases in MARL training algorithms that cause sub-optimal convergence to specialist strategies with larger state spaces.
@article{arxiv.2503.15703,
title = {Predicting Multi-Agent Specialization via Task Parallelizability},
author = {Elizabeth Mieczkowski and Ruaridh Mon-Williams and Neil Bramley and Christopher G. Lucas and Natalia Velez and Thomas L. Griffiths},
journal= {arXiv preprint arXiv:2503.15703},
year = {2025}
}