Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
This work aids computational social science in bridging simulations with real-world dynamics and offers the AI community a novel method to assess LLMs' deliberate reasoning capabilities.
The paper tackled the problem of whether LLM agents can spontaneously cooperate in competitive scenarios without explicit instructions, and found that they successfully simulated the gradual emergence of cooperation that aligns closely with human behavioral data.
Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the necessity of shaping agents' behaviors for accurate social simulations. Instead, this paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions. We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation, findings that align closely with human behavioral data. This approach not only aids the computational social science community in bridging the gap between simulations and real-world dynamics but also offers the AI community a novel method to assess LLMs' capability of deliberate reasoning.