# MAC: Multi-Agent Constitution Learning

arXiv: https://arxiv.org/abs/2603.15968 · HTML: https://mlsanity.com/paper/2603.15968/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [ProPILE: Probing Privacy Leakage in Large Language Models](https://mlsanity.com/paper/2307.01881/) (2023)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [Unveiling Privacy Risks in LLM Agent Memory](https://mlsanity.com/paper/2502.13172/) (2025)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles](https://mlsanity.com/paper/2410.17127/) (2024)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface](https://mlsanity.com/paper/2507.18546/) (2025)

## Built on by (most cited first, 2 of 2)

- [Behavioral Governance for Autonomous AI Agents: The AgentBound Framework](https://mlsanity.com/paper/2606.30970/) (2026)
- [Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design](https://mlsanity.com/paper/2605.09128/) (2026)

## Abstract (arXiv)

Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training data for the desired behavior. Existing LLM-based prompt optimizers attempt this but are ineffective at learning constitutions since (i) they require many labeled examples and (ii) lack structure in the optimized prompts, leading to diminishing improvements as prompt size grows. To address these limitations, we propose Multi-Agent Constitutional Learning (MAC), which optimizes over structured prompts represented as sets of rules using a network of agents with specialized tasks to accept, edit, or reject rule updates. We also present MAC+, which improves performance by training agents on successful trajectories to reinforce updates leading to higher reward. We evaluate MAC on tagging Personally Identifiable Information (PII), a classification task with limited labels where interpretability is critical, and demonstrate that it generalizes to other agentic tasks such as tool calling. MAC outperforms recent prompt optimization methods by over 50%, produces human-readable and auditable rule sets, and achieves performance comparable to supervised fine-tuning and GRPO without requiring parameter updates.