Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
Abstract
Multi-agent AI systems need behavioral constitutions, but it is unresolved whether such rules should emerge internally through agent self-governance or be discovered externally through optimization. We present the first controlled comparison of internal deliberation and external evolution across three social environments: a coordination grid-world, an iterated public goods game, and a bilateral trading market. Across 180 simulation runs, evolution significantly outperforms deliberation in collective-action settings (p < 0.01), while neither method improves outcomes in bilateral trading. A multiplier ablation reveals that evolution's advantage inverts when incentives shift: at pool multiplier (m = 0.75) the evolved constitution forces value-destroying cooperation and becomes the worst-performing method. Notably, no deliberation run across thirty trials ever proposed punishment -- the canonical cooperation-sustaining mechanism evolution reliably discovers -- suggesting external optimization wins on peaks while internal self-governance trades peaks for structural responsiveness.
Cite
@article{arxiv.2605.09128,
title = {Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design},
author = {Hershraj Niranjani and Ujwal Kumar and Phan Xuan Tan},
journal= {arXiv preprint arXiv:2605.09128},
year = {2026}
}
Comments
20 pages