mlsanityData to 7 Oct 2026

Beyond the Townhall: Spatial Anchoring and LLM Agents for Scalable Participatory Urban Planning

arXiv 2604.16348 ↗First posted 16 Mar 2026cs.HC cs.CYcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

LLMs are increasingly explored for public participation, but less is known about how they should be designed around the information citizens encounter beforehand. In an experiment (N=200) on participatory urban planning, participants learned about a sustainability project adapted from a real street redesign, through text and images or narrated 360-degree video with spatial audio and spatial anchoring; they subsequently engaged with factual and reflective LLM personas. The immersive condition improved recall and changed what participants said to the agents: they named beneficiaries more often, asked directionally more project-related questions, and provided more positive feedback. We contribute (1) a conceptualization of LLMs as dialogue partners complementing a shared information baseline, (2) causal evidence that this baseline shapes those conversations, (3) an account of how citizens use and judge factual versus reflective agent roles, and (4) a method for cities to test information packages and agent configurations before public release.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 12 of its 152 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

12 of 152 references.

References · 12

  1. 2021XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyondcited by 114
  2. 2020Participation is not a Design Fix for Machine Learningcited by 110
  3. 2024On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trialcited by 105
  4. 2024LLM Voting: Human Choices and AI Collective Decision Makingcited by 47
  5. 2025A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societiescited by 8
  6. 2020Submitting surveys via a conversational interface: an evaluation of user acceptance and approach effectivenesscited by 6
  7. 2026The CitizenQuery Benchmark: A Novel Dataset and Evaluation Pipeline for Measuring LLM Performance in Citizen Query Taskscited by 4
  8. 2025A Replica for our Democracies? On Using Digital Twins to Enhance Deliberative Democracycited by 3
  9. 2025WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Designcited by 3
  10. 2025Learn, Explore and Reflect by Chatting: Understanding the Value of an LLM-Based Voting Advice Application Chatbotcited by 1
  11. 2025Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Makingcited by 1
  12. 2026Learning Through Dialogue: Engagement and Efficacy Matter More Than Explanationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban Planning
  2. 2024Large language model empowered participatory urban planning
  3. 2024Large Language Model for Participatory Urban Planning
  4. 2024Simulating Multi-Stakeholder Decision-Making with Generative Agents in Urban Planning
  5. 2026CoDesignAI: An AI-Enabled Multi-Agent, Multi-User System for Collaborative Urban Design at the Conceptual Stage
  6. 2026LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data
  7. 2026Three Lessons from Citizen-Centric Participatory AI Design
  8. 2026Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional Judgment