MAC: Multi-Agent Constitution Learning

Large Language Models (LLMs) can generate persuasive influence strategies that shift cooperative behavior in multi-agent populations, but a critical question remains: does the resulting cooperation reflect genuine prosocial alignment, or does it mask erosion of agent autonomy, epistemic integrity, and distributional fairness? We introduce Constitutional Multi-Agent Governance (CMAG), a two-stage framework that interposes between an LLM policy compiler and a networked agent population, combining hard constraint filtering with soft penalized-utility optimization that balances cooperation potential against manipulation risk and autonomy pressure. We propose the Ethical Cooperation Score (ECS), a multiplicative composite of cooperation, autonomy, integrity, and fairness that penalizes cooperation achieved through manipulative means. In experiments on scale-free networks of 80 agents under adversarial conditions (70% violating candidates), we benchmark three regimes: full CMAG, naive filtering, and unconstrained optimization. While unconstrained optimization achieves the highest raw cooperation (0.873), it yields the lowest ECS (0.645) due to severe autonomy erosion (0.867) and fairness degradation (0.888). CMAG attains an ECS of 0.741, a 14.9% improvement, while preserving autonomy at 0.985 and integrity at 0.995, with only modest cooperation reduction to 0.770. The naive ablation (ECS = 0.733) confirms that hard constraints alone are insufficient. Pareto analysis shows CMAG dominates the cooperation-autonomy trade-off space, and governance reduces hub-periphery exposure disparities by over 60%. These findings establish that cooperation is not inherently desirable without governance: constitutional constraints are necessary to ensure that LLM-mediated influence produces ethically stable outcomes rather than manipulative equilibria.

Pairwise preference data is widely used for training and evaluating language models (e.g., RLHF), but each datapoint records a choice, not the rationale behind it. Methods such as Inverse Constitutional AI (ICAI) attempt to improve interpretability by compressing datasets into short ``constitutions'' of natural-language principles. We argue this framing is under-specified: a flat list of principles is not yet an executable decision rule because it leaves principle composition implicit. We use the pairwise setting as a testbed to empirically characterize three open problems in constitutional methods. First, principle quality is hard to measure: coverage and accuracy are useful but incomplete proxies for end-to-end reconstruction. Second, composition is ambiguous: holding principles fixed, different executors (LLM judge versus majority vote) agree only $73\%$ of the time. Third, constitutions differ between LLMs: cross-model vote agreement is $73\%$, whereas intra-model agreement is $81\%$. Across PRISM, AlpacaEval, and Chatbot Arena, we show that principle refinement (ICAI+) may be a first step towards ameliorating these problems: inter-executor agreement rises to $78\%$, and transparent executors match LLM judge accuracy ($66\%$ vs.\ $67\%$). Our results highlight that constitutions should be evaluated as constitution--executor systems, with implications for LLMs-as-a-judge broadly.

Large language models, the artificial intelligence (AI) systems behind modern chatbots, are trained on vast amounts of legal text, but can they build on it to write law for situations that text never anticipated? In this study, we analyse AI agents' ability to draft a hypothetical "Constitution" for a "community of AI agents". We design "constitutional assemblies" in which a single language model plays several characters that debate to produce a draft constitution. We find that the assemblies converge on a robust floor of legal provisions, and generate a wide variety of different proposals around it, including several AI-specific provisions with no equivalent in human law. Looking more closely at the "creativity" of these AI agents, we find different levels: most proposals combine existing concepts and themes from human constitutions with AI-specific vocabulary. We introduce a measure of this recombination, which helps identify and highlight the most novel legal material. This study reveals a ceiling on AI creativity: the agents extend familiar legal ideas to new situations, but they do not work through what those situations would change. Although current AI models can help develop new laws, they still depend on human legal reasoning.