Retrieval-Augmented Simulacra: Generative Agents for Up-to-date and Knowledge-Adaptive Simulations
This work addresses the need for predicting trends in SNS interactions, particularly in Japan, but it appears incremental as it builds on an existing simulation system.
The paper tackled the problem of simulating social networking service (SNS) interactions by evaluating a search extension generation mechanism in a virtual SNS environment, and found that this mechanism, which mimics human search behavior, generated the most natural exchanges.
In the 2023 edition of the White Paper on Information and Communications, it is estimated that the population of social networking services in Japan will exceed 100 million by 2022, and the influence of social networking services in Japan is growing significantly. In addition, marketing using SNS and research on the propagation of emotions and information on SNS are being actively conducted, creating the need for a system for predicting trends in SNS interactions. We have already created a system that simulates the behavior of various communities on SNS by building a virtual SNS environment in which agents post and reply to each other in a chat community created by agents using a LLMs. In this paper, we evaluate the impact of the search extension generation mechanism used to create posts and replies in a virtual SNS environment using a simulation system on the ability to generate posts and replies. As a result of the evaluation, we confirmed that the proposed search extension generation mechanism, which mimics human search behavior, generates the most natural exchange.