# Agentmandering: A Game-Theoretic Framework for Fair Redistricting via Large Language Model Agents

arXiv: https://arxiv.org/abs/2511.04076 · HTML: https://mlsanity.com/paper/2511.04076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

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

- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis](https://mlsanity.com/paper/2312.05488/) (2023)
- [Game-theoretic LLM: Agent Workflow for Negotiation Games](https://mlsanity.com/paper/2411.05990/) (2024)
- [ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents](https://mlsanity.com/paper/2311.03220/) (2023)
- [Steering Language Models with Game-Theoretic Solvers](https://mlsanity.com/paper/2402.01704/) (2024)
- [Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search](https://mlsanity.com/paper/2408.10635/) (2024)
- [Recombination: A family of Markov chains for redistricting](https://mlsanity.com/paper/1911.05725/) (2019)
- [Sequential Monte Carlo for Sampling Balanced and Compact Redistricting Plans](https://mlsanity.com/paper/2008.06131/) (2020)
- [Assessing significance in a Markov chain without mixing](https://mlsanity.com/paper/1608.02014/) (2016)
- [Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game](https://mlsanity.com/paper/2501.19398/) (2025)
- [A partisan districting protocol with provably nonpartisan outcomes](https://mlsanity.com/paper/1710.08781/) (2017)
- [All Politics is Local: Redistricting via Local Fairness](https://mlsanity.com/paper/2210.11643/) (2022)
- [Utility Ghost: Gamified redistricting with partisan symmetry](https://mlsanity.com/paper/1812.07377/) (2018)
- [You Can Have Your Cake and Redistrict It Too](https://mlsanity.com/paper/2305.12079/) (2023)
- [Optimizing Representation in Redistricting: Dual Bounds for Partitioning Problems with Non-Convex Objectives](https://mlsanity.com/paper/2305.17298/) (2023)

## Abstract (arXiv)

Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight creates opportunities for partisan actors to cherry-pick maps that, while technically compliant, are politically advantageous. Simply satisfying formal constraints does not ensure fairness when the selection process itself can be manipulated. We propose Agentmandering, a framework that reimagines redistricting as a turn-based negotiation between two agents representing opposing political interests. Drawing inspiration from game-theoretic ideas, particularly the textitChoose-and-Freeze protocol, our method embeds strategic interaction into the redistricting process via large language model (LLM) agents. Agents alternate between selecting and freezing districts from a small set of candidate maps, gradually partitioning the state through constrained and interpretable choices. Evaluation on post-2020 U.S. Census data across all states shows that Agentmandering significantly reduces partisan bias and unfairness, while achieving 2 to 3 orders of magnitude lower variance than standard baselines. These results demonstrate both fairness and stability, especially in swing-state scenarios. Our code is available at https://github.com/Lihaogx/AgentMandering.