# What Makes LLM Agent Simulations Useful for Policy Practice? An Iterative Design Study in Emergency Preparedness arXiv: https://arxiv.org/abs/2509.21868 ยท HTML: https://mlsanity.com/paper/2509.21868/ ## Key facts - Cited by 2 papers in the map (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 30 of its 108 references that are in the map. - First posted on arXiv 26 Sep 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, 30 of 30) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023) - [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022) - [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018) - [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023) - [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024) - [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023) - [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024) - [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020) - [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025) - [Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims](https://mlsanity.com/paper/2004.07213/) (2020) - ['It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions](https://mlsanity.com/paper/1801.10408/) (2018) - [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024) - [GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://mlsanity.com/paper/2410.04360/) (2024) - [Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment](https://mlsanity.com/paper/2312.11813/) (2023) - [AutoDS: Towards Human-Centered Automation of Data Science](https://mlsanity.com/paper/2101.05273/) (2021) - [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025) - ['Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants](https://mlsanity.com/paper/2409.19430/) (2024) - [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024) - [LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra](https://mlsanity.com/paper/2507.15815/) (2025) - [Agile Software Development Methods: Review and Analysis](https://mlsanity.com/paper/1709.08439/) (2017) - [Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy](https://mlsanity.com/paper/2503.09639/) (2025) - [Large Language Model-driven Multi-Agent Simulation for News Diffusion Under Different Network Structures](https://mlsanity.com/paper/2410.13909/) (2024) - [WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI](https://mlsanity.com/paper/2501.01397/) (2025) - [Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective](https://mlsanity.com/paper/2402.00262/) (2024) - [Contestable Camera Cars: A Speculative Design Exploration of Public AI That Is Open and Responsive to Dispute](https://mlsanity.com/paper/2302.04603/) (2023) - [Unpacking Invisible Work Practices, Constraints, and Latent Power Relationships in Child Welfare through Casenote Analysis](https://mlsanity.com/paper/2203.05169/) (2022) - [PolicyCraft: Supporting Collaborative and Participatory Policy Design through Case-Grounded Deliberation](https://mlsanity.com/paper/2409.15644/) (2024) - [The Future of HCI-Policy Collaboration](https://mlsanity.com/paper/2409.19738/) (2024) - [Agent-based models of social behaviour and communication in evacuations: A systematic review](https://mlsanity.com/paper/2310.15761/) (2023) ## Built on by (most cited first, 2 of 2) - [WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning](https://mlsanity.com/paper/2604.17615/) (2026) - [From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2609.13261/) (2026) ## Abstract (arXiv) Policymakers must often act under conditions of deep uncertainty, such as emergency response, where predicting the specific impacts of a policy apriori is implausible. Large Language Model (LLM) agent simulations have been proposed as tools to support policymakers under these conditions, yet little is known about how such simulations become useful for real-world policy practice. To address this gap, we conducted a year-long, stakeholder-engaged design process with a university emergency preparedness team. Through iterative design cycles, we developed and refined an LLM agent simulation of a large-scale campus gathering, ultimately scaling to 13,000 agents that modeled crowd movement and communication under various emergency scenarios. Rather than producing predictive forecasts, these simulations supported policy practice by shaping volunteer training, evacuation procedures, and infrastructure planning. Analyzing these findings, we identify three design process implications for making LLM agent simulations that are useful for policy practice: start from verifiable scenarios to bootstrap trust, use preliminary simulations to elicit tacit domain knowledge, and treat simulation capabilities and policy implementation as co-evolving.