Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
By: Ryosuke Takata, Atsushi Masumori, Takashi Ikegammi
Potential Business Impact:
Computers learn to make group decisions like people.
We investigate the emergent social dynamics of Large Language Model (LLM) agents in a spatially extended El Farol Bar problem, observing how they autonomously navigate this classic social dilemma. As a result, the LLM agents generated a spontaneous motivation to go to the bar and changed their decision making by becoming a collective. We also observed that the LLM agents did not solve the problem completely, but rather behaved more like humans. These findings reveal a complex interplay between external incentives (prompt-specified constraints such as the 60\% threshold) and internal incentives (culturally-encoded social preferences derived from pre-training), demonstrating that LLM agents naturally balance formal game-theoretic rationality with social motivations that characterize human behavior. These findings suggest that a new model of group decision making, which could not be handled in the previous game-theoretic problem setting, can be realized by LLM agents.
Similar Papers
Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
Multiagent Systems
AI learns to make group decisions like people.
Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
Multiagent Systems
AI agents learn to make group decisions like people.
Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
Multiagent Systems
Helps computers study how people act together.