# Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design

arXiv: https://arxiv.org/abs/2605.09128 · HTML: https://mlsanity.com/paper/2605.09128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 15 of 15)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [AutoML-Zero: Evolving Machine Learning Algorithms From Scratch](https://mlsanity.com/paper/2003.03384/) (2020)
- [Evolution through Large Models](https://mlsanity.com/paper/2206.08896/) (2022)
- [Inequity aversion improves cooperation in intertemporal social dilemmas](https://mlsanity.com/paper/1803.08884/) (2018)
- [Stay Focused: Problem Drift in Multi-Agent Debate](https://mlsanity.com/paper/2502.19559/) (2025)
- [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025)
- [Literature Review Of Multi-Agent Debate For Problem-Solving](https://mlsanity.com/paper/2506.00066/) (2025)
- [Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation](https://mlsanity.com/paper/2402.12590/) (2024)
- [Enhancing LLM Planning Capabilities through Intrinsic Self-Critique](https://mlsanity.com/paper/2512.24103/) (2025)
- [Evolving Interpretable Constitutions for Multi-Agent Coordination](https://mlsanity.com/paper/2602.00755/) (2026)
- [LLM Constitutional Multi-Agent Governance](https://mlsanity.com/paper/2603.13189/) (2026)
- [MAC: Multi-Agent Constitution Learning](https://mlsanity.com/paper/2603.15968/) (2026)

## Abstract (arXiv)

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.