EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
This addresses efficiency issues in social simulations for researchers and practitioners, though it is incremental as it builds on existing agent-based models.
The paper tackles the high time and computation costs in large-scale social simulations using LLMs by proposing EcoLANG, a two-stage method involving language evolution and utilization, which reduces token consumption by over 20% without compromising accuracy.
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.