Simulate Large LLM Agent Societies Cheaply on a Laptop.

Igor Itkin· August 13, 2026 View original

Key takeaways

  • Large LLM agent societies can be simulated cheaply using low-parameter surrogate models.
  • Surrogate models are fitted from a small number of LLM queries.
  • A taxonomy helps predict the accuracy and N-trend of surrogate errors.
  • This approach makes large-scale agentic modeling accessible on a laptop.

Who benefits

AcademiaResearch & DevelopmentAI/ML DevelopmentSocial Sciences

Summary

Simulating large societies of LLM agents is expensive, but this paper proposes a method to replace each LLM agent with a low-parameter surrogate model. These surrogates are fitted from a few hundred to a few thousand cheap queries, enabling large-scale simulations on a laptop while accurately capturing macroscopic behaviors.

Simulating complex societies composed of numerous large language model (LLM) agents typically demands substantial computational resources, making it costly and often impractical for extensive research. This paper introduces a novel, cost-effective approach called "Poor Man's Agentic Modeling" that allows for the simulation of vast LLM agent societies on standard laptops. The core of the method involves replacing each individual LLM agent with a simplified, low-parameter surrogate model. These surrogates are trained by fitting them to a relatively small number of queries (hundreds to thousands) from genuine LLMs. The paper also presents an interaction order x memory taxonomy that helps predict the accuracy of these surrogate models, validating the approach across several existing LLM simulations, including a reimplementation of the EconAgent macroeconomy.

Why it matters

This method significantly reduces the cost and computational barrier to entry for researchers and developers interested in studying emergent behaviors in large-scale LLM agent societies.

How to implement this in your domain

  1. 1Adopt surrogate modeling techniques for large-scale agent-based simulations.
  2. 2Develop low-parameter models to mimic complex LLM agent behaviors.
  3. 3Utilize the proposed taxonomy to assess the feasibility and expected error of surrogate models.
  4. 4Experiment with this approach to explore phase behaviors and scaling laws in agent societies.

Original post by Igor Itkin

"arXiv:2608.11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents $N$, not the co…"

View on X

Originally posted by Igor Itkin on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses