# Large Language Models for Designing Participatory Budgeting Rules

arXiv: https://arxiv.org/abs/2602.09349 · HTML: https://mlsanity.com/paper/2602.09349/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [Justified Representation in Approval-Based Committee Voting](https://mlsanity.com/paper/1407.8269/) (2014)
- [Proportional Participatory Budgeting with Additive Utilities](https://mlsanity.com/paper/2008.13276/) (2020)
- [Proportional Justified Representation](https://mlsanity.com/paper/1611.09928/) (2016)
- [Participatory Budgeting: Models and Approaches](https://mlsanity.com/paper/2003.00606/) (2020)
- [Robust and Verifiable Proportionality Axioms for Multiwinner Voting](https://mlsanity.com/paper/2302.01989/) (2023)
- [Proportionality and the Limits of Welfarism](https://mlsanity.com/paper/1911.11747/) (2019)
- [Finding a Collective Set of Items: From Proportional Multirepresentation to Group Recommendation](https://mlsanity.com/paper/1402.3044/) (2014)
- [What Do Multiwinner Voting Rules Do? An Experiment Over the Two-Dimensional Euclidean Domain](https://mlsanity.com/paper/1901.09217/) (2019)
- [Proportionally Representative Participatory Budgeting: Axioms and Algorithms](https://mlsanity.com/paper/1711.08226/) (2017)
- [Fair Knapsack](https://mlsanity.com/paper/1711.04520/) (2017)
- [A Framework for Approval-based Budgeting Methods](https://mlsanity.com/paper/1809.04382/) (2018)
- [Proportionality Degree of Multiwinner Rules](https://mlsanity.com/paper/1810.08799/) (2018)
- [Guide to Numerical Experiments on Elections in Computational Social Choice](https://mlsanity.com/paper/2402.11765/) (2024)
- [A verifiably secure and proportional committee election rule](https://mlsanity.com/paper/2004.12990/) (2020)
- [Proportionality in Approval-Based Participatory Budgeting](https://mlsanity.com/paper/2302.03672/) (2023)
- [Welfare vs. Representation in Participatory Budgeting](https://mlsanity.com/paper/2201.07546/) (2022)
- [Shortlisting Rules and Incentives in an End-to-End Model for Participatory Budgeting](https://mlsanity.com/paper/2010.10309/) (2020)
- [Discrete Budget Aggregation: Truthfulness and Proportionality](https://mlsanity.com/paper/2505.05708/) (2025)

## Built on by (most cited first, 1 of 1)

- [Preference Reasoning under Indeterminacy in Large Language Models](https://mlsanity.com/paper/2608.18631/) (2026)

## Abstract (arXiv)

Participatory budgeting (PB) is a democratic paradigm for deciding the funding of public projects given the residents' preferences, which has been adopted in numerous cities across the world. The main focus of PB is designing rules, functions that return feasible budget allocations for a set of projects subject to some budget constraint. Designing PB rules that optimize both utility and fairness objectives based on agent preferences had been challenging due to the extensive domain knowledge required and the proven trade-off between the two notions. Recently, large language models (LLMs) have been increasingly employed for automated algorithmic design. Given the resemblance of PB rules to algorithms for classical knapsack problems, in this paper, we introduce a novel framework, named LLMRule, that addresses the limitations of existing works by incorporating LLMs into an evolutionary search procedure for automating the design of PB rules. Our experimental results, evaluated on more than 600 real-world PB instances obtained from the U.S., Canada, Poland, and the Netherlands with different representations of agent preferences, demonstrate that the LLM-generated rules generally outperform existing handcrafted rules in terms of overall utility while still maintaining a similar degree of fairness.