cs.AIJul 19, 2026

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop

Authors: Igor Itkin

Organizations: Independent Researcher, Tel Aviv, Israel

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 NN, not the cognition of any single agent. We turn a statistical-physics observation into a method: replace each LLM agent by a low-parameter model fitted from a few hundred to a few thousand cheap queries, then run the society at any NN on a laptop. Whether this works is decided before the simulation runs, chiefly by what each agent perceives. We introduce an [interaction order x memory] taxonomy that maps perception and memory to an effective theory and a predicted NN-trend of the surrogate error. We validate it on a faithful reimplementation of the LLM macroeconomy EconAgent and seven further named LLM simulations, with agent decisions cloned from genuine LLM elicitations (primarily DeepSeek) for a few dollars; the predicted error trends hold cell by cell, and the two refuted predictions, both on a strongly saturating response and traced to its curvature, are themselves matched quantitatively by the theory with no free parameters.

Explore similar work

CardsList
  1. Collective cooperation without individual fidelity in LLM agents

    Jun 29, 2026Henrique Ferraz de Arruda, Carlos Gracia Lázaro, Alberto Aleta +1Large Language Model AgentsCooperation