# An Interpretable Automated Mechanism Design Framework with Large Language Models

arXiv: https://arxiv.org/abs/2502.12203 · HTML: https://mlsanity.com/paper/2502.12203/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 73 references that are in the map.
- First posted on arXiv 16 Feb 2025.

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

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Learning Performance-Improving Code Edits](https://mlsanity.com/paper/2302.07867/) (2023)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Optimal Auctions through Deep Learning: Advances in Differentiable Economics](https://mlsanity.com/paper/1706.03459/) (2017)
- [Complexity of Mechanism Design](https://mlsanity.com/paper/1408.1486/) (2014)
- [Automated Mechanism Design via Neural Networks](https://mlsanity.com/paper/1805.03382/) (2018)
- [A Permutation-Equivariant Neural Network Architecture For Auction Design](https://mlsanity.com/paper/2003.01497/) (2020)
- [Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs](https://mlsanity.com/paper/2408.00114/) (2024)
- [Learning Simple Auctions](https://mlsanity.com/paper/1604.03171/) (2016)
- [Brief analysis of DeepSeek R1 and its implications for Generative AI](https://mlsanity.com/paper/2502.02523/) (2025)
- [Automated Dynamic Mechanism Design](https://mlsanity.com/paper/2105.06008/) (2021)
- [Sampling and Representation Complexity of Revenue Maximization](https://mlsanity.com/paper/1402.4535/) (2014)
- [Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information](https://mlsanity.com/paper/2412.16132/) (2024)
- [Worst-Case VCG Redistribution Mechanism Design Based on the Lottery Ticket Hypothesis](https://mlsanity.com/paper/2305.11011/) (2023)

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

- [Discovering Differences in Strategic Behavior Between Humans and LLMs](https://mlsanity.com/paper/2602.10324/) (2026)
- [Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models](https://mlsanity.com/paper/2604.06263/) (2026)

## Abstract (arXiv)

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for designing payments and allocations. While both analytical and automated methods have advanced the field, they each face significant weaknesses: mathematical derivations are not automated and often struggle to scale to complex problems, while automated and especially neural-network-based approaches suffer from limited interpretability. To address these challenges, we introduce a novel framework that reformulates mechanism design as a code generation task. Using large language models (LLMs), we generate heuristic mechanisms described in code and evolve them to optimize over some evaluation metrics while ensuring key design criteria (e.g., strategy-proofness) through a problem-specific fixing process. This fixing process ensures any mechanism violating the design criteria is adjusted to satisfy them, albeit with some trade-offs in performance metrics. These trade-offs are factored in during the LLM-based evolution process. The code generation capabilities of LLMs enable the discovery of novel and interpretable solutions, bridging the symbolic logic of mechanism design and the generative power of modern AI. Through rigorous experimentation, we demonstrate that LLM-generated mechanisms achieve competitive performance while offering greater interpretability compared to previous approaches. Notably, our framework can rediscover existing manually designed mechanisms and provide insights into neural-network based solutions through Programming-by-Example. These results highlight the potential of LLMs to not only automate but also enhance the transparency and scalability of mechanism design, ensuring safe deployment of the mechanisms in society.