EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation

TL;DR

EcoLANG introduces a novel method for inducing efficient agent communication languages that significantly reduces token usage in social simulations while maintaining accuracy, addressing key computational challenges in large-scale social modeling.

Contribution

EcoLANG presents a two-stage language induction process that optimizes communication efficiency in social simulations without compromising accuracy or generalizability.

Findings

Reduces token consumption by over 20%.

Maintains simulation accuracy with optimized language.

Enhances efficiency in large-scale social simulations.

Abstract

Large language models (LLMs) have demonstrated an impressive ability to role-play humans and replicate complex social dynamics. While large-scale social simulations are gaining increasing attention, they still face significant challenges, particularly regarding high time and computation costs. Existing solutions, such as distributed mechanisms or hybrid agent-based model (ABM) integrations, either fail to address inference costs or compromise accuracy and generalizability. To this end, we propose EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation. EcoLANG operates in two stages: (1) language evolution, where we filter synonymous words and optimize sentence-level rules through natural selection, and (2) language utilization, where agents in social simulations communicate using the evolved language. Experimental results demonstrate that EcoLANG reduces token consumption by over 20%, enhancing efficiency without sacrificing simulation accuracy.