# Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies

arXiv: https://arxiv.org/abs/2503.12613 · HTML: https://mlsanity.com/paper/2503.12613/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 80 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [Large Language Model for Participatory Urban Planning](https://mlsanity.com/paper/2402.17161/) (2024)
- [CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1809.05188/) (2018)
- [Vote'n'Rank: Revision of Benchmarking with Social Choice Theory](https://mlsanity.com/paper/2210.05769/) (2022)
- [Algorithmic Pluralism: A Structural Approach To Equal Opportunity](https://mlsanity.com/paper/2305.08157/) (2023)
- [Goldilocks: Consistent Crowdsourced Scalar Annotations with Relative Uncertainty](https://mlsanity.com/paper/2108.01799/) (2021)
- [LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban Planning](https://mlsanity.com/paper/2412.20505/) (2024)
- [LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces](https://mlsanity.com/paper/2503.01894/) (2025)
- [AI Agent as Urban Planner: Steering Stakeholder Dynamics in Urban Planning via Consensus-based Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2310.16772/) (2023)
- [Survey of Distributed Algorithms for Resource Allocation over Multi-Agent Systems](https://mlsanity.com/paper/2401.15607/) (2024)
- [The Right to AI](https://mlsanity.com/paper/2501.17899/) (2025)
- [Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction](https://mlsanity.com/paper/2410.05550/) (2024)
- [Dynamic Urban Planning: an Agent-Based Model Coupling Mobility Mode and Housing Choice. Use case Kendall Square](https://mlsanity.com/paper/2106.14572/) (2021)
- [AI-EDI-SPACE: A Co-designed Dataset for Evaluating the Quality of Public Spaces](https://mlsanity.com/paper/2411.00956/) (2024)

## Built on by (most cited first, 4 of 4)

- [Do Vision-Language Models See Urban Scenes as People Do? An Urban Perception Benchmark](https://mlsanity.com/paper/2509.14574/) (2025)
- [Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity](https://mlsanity.com/paper/2508.11708/) (2025)
- [Co-Producing AI: Toward an Augmented, Participatory Lifecycle](https://mlsanity.com/paper/2508.00138/) (2025)
- [Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction](https://mlsanity.com/paper/2607.00001/) (2026)

## Abstract (arXiv)

Urban assessments often compress diverse needs into single scores, which can obscure minority perspectives. We present a community-centered study in Montreal (n=35; wheelchair users, seniors, LGBTQIA2+ residents, and immigrants). Participants rated 20 streets (accessibility, inclusivity, aesthetics, practicality) and ranked 7 images on 12 interview-elicited criteria. Disagreement patterns were systematic in our sample: wheelchair users diverged most on accessibility and practicality; LGBTQIA2+ participants emphasized inclusion and liveliness; seniors prioritized security. Group discussion reduced information gaps but not value conflicts; ratings conveyed intensity, while rankings forced trade-offs. We then formalize negotiative alignment, a transparent, budget-aware bargaining procedure, and pilot it with role-played stakeholder agents plus a neutral mediator. Relative to the best base design under the same public rubric, the negotiated package increased total utility (21.10 to 24.55), raised the worst-group utility (3.20 to 3.90), improved twentieth percentile satisfaction (0.86 to 1.00; min-max normalized within the scenario), and reduced inequality (Gini 0.036 to 0.025). Treating disagreement as signal and reporting worst-group outcomes alongside totals may help planners and AI practitioners surface trade-offs and preserve minority priorities while maintaining efficiency.