Agentmandering: A Game-Theoretic Framework for Fair Redistricting via Large Language Model Agents
Preprint
Abstract
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 \textbf{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 \textit{Choose-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.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Optimizing representation in redistricting: dual bounds for partitioning problems with non-convex objectivesMathematical Methods of Operations Research, 2026
- A Partisan Solution to Partisan Gerrymandering: The Define–Combine ProcedurePolitical Analysis, 2023
- More human than human: measuring ChatGPT political biasPublic Choice, 2023
- You Can Have Your Cake and Redistrict It Too2023
- Gerrymandering and Compactness: Implementation Flexibility and AbusePolitical Analysis, 2020
- Automated Redistricting Simulation Using Markov Chain Monte CarloJournal of Computational and Graphical Statistics, 2020
- Assessing significance in a Markov chain without mixingProceedings of the National Academy of Sciences, 2017
- Cutting Through the Thicket: Redistricting Simulations and the Detection of Partisan GerrymandersElection Law Journal: Rules, Politics, and Policy, 2015
- A fair division solution to the problem of redistrictingSocial Choice and Welfare, 2008
- The Future of Partisan Symmetry as a Judicial Test for Partisan Gerrymandering after LULAC v. PerryElection Law Journal: Rules, Politics, and Policy, 2007