# On the limits of agency in agent-based models arXiv: https://arxiv.org/abs/2409.10568 ยท HTML: https://mlsanity.com/paper/2409.10568/ ## Key facts - Cited by 21 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 17 of its 57 references that are in the map. - First posted on arXiv 14 Sep 2024. ## 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, 17 of 17) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023) - [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019) - [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://mlsanity.com/paper/1903.05662/) (2019) - [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023) - [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023) - [Automatic Differentiation of Programs with Discrete Randomness](https://mlsanity.com/paper/2210.08572/) (2022) - [Differentiable Agent-based Epidemiology](https://mlsanity.com/paper/2207.09714/) (2022) - [HyperNCA: Growing Developmental Networks with Neural Cellular Automata](https://mlsanity.com/paper/2204.11674/) (2022) - [On learning agent-based models from data](https://mlsanity.com/paper/2205.05052/) (2022) - [DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks](https://mlsanity.com/paper/2110.04421/) (2021) - [COVID-19 is linked to changes in the time-space dimension of human mobility](https://mlsanity.com/paper/2201.06527/) (2022) - [Agents.jl: A performant and feature-full agent based modelling software of minimal code complexity](https://mlsanity.com/paper/2101.10072/) (2021) - [Bayesian calibration of differentiable agent-based models](https://mlsanity.com/paper/2305.15340/) (2023) - [Efficient Learning of Discrete-Continuous Computation Graphs](https://mlsanity.com/paper/2307.14193/) (2023) ## Built on by (most cited first, 21 of 21) - [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024) - [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024) - [OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents](https://mlsanity.com/paper/2410.21286/) (2024) - [LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra](https://mlsanity.com/paper/2507.15815/) (2025) - [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024) - [RecoWorld: Building Simulated Environments for Agentic Recommender Systems](https://mlsanity.com/paper/2509.10397/) (2025) - [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) - [Modeling Earth-Scale Human-Like Societies with One Billion Agents](https://mlsanity.com/paper/2506.12078/) (2025) - [Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits](https://mlsanity.com/paper/2605.18890/) (2026) - [Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust](https://mlsanity.com/paper/2507.02197/) (2025) - [TravelAgent: Generative Agents in the Built Environment](https://mlsanity.com/paper/2412.18985/) (2024) - [Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2507.21354/) (2025) - [PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling](https://mlsanity.com/paper/2602.06030/) (2026) - [Ripple Effect Protocol: Coordinating Agent Populations](https://mlsanity.com/paper/2510.16572/) (2025) - [What Would an LLM Do? Evaluating Large Language Models for Policymaking to Alleviate Homelessness](https://mlsanity.com/paper/2509.03827/) (2025) - [Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain](https://mlsanity.com/paper/2508.16172/) (2025) - [Hierarchical Generative Agents for Simulating Sequential Human Behavior](https://mlsanity.com/paper/2606.14989/) (2026) - [GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies](https://mlsanity.com/paper/2606.27650/) (2026) - [Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop](https://mlsanity.com/paper/2608.11215/) (2026) - [Local Predictability and Collective Fidelity in LLM-Agent Societies](https://mlsanity.com/paper/2609.35813/) (2026) - [Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia](https://mlsanity.com/paper/2610.05041/) (2026) ## Abstract (arXiv) Agent-based modeling (ABM) offers powerful insights into complex systems, but its practical utility has been limited by computational constraints and simplistic agent behaviors, especially when simulating large populations. Recent advancements in large language models (LLMs) could enhance ABMs with adaptive agents, but their integration into large-scale simulations remains challenging. This work introduces a novel methodology that bridges this gap by efficiently integrating LLMs into ABMs, enabling the simulation of millions of adaptive agents. We present LLM archetypes, a technique that balances behavioral complexity with computational efficiency, allowing for nuanced agent behavior in large-scale simulations. Our analysis explores the crucial trade-off between simulation scale and individual agent expressiveness, comparing different agent architectures ranging from simple heuristic-based agents to fully adaptive LLM-powered agents. We demonstrate the real-world applicability of our approach through a case study of the COVID-19 pandemic, simulating 8.4 million agents representing New York City and capturing the intricate interplay between health behaviors and economic outcomes. Our method significantly enhances ABM capabilities for predictive and counterfactual analyses, addressing limitations of historical data in policy design. By implementing these advances in an open-source framework, we facilitate the adoption of LLM archetypes across diverse ABM applications. Our results show that LLM archetypes can markedly improve the realism and utility of large-scale ABMs while maintaining computational feasibility, opening new avenues for modeling complex societal challenges and informing data-driven policy decisions.