Saved in:
Bibliographic Details
Main Authors: Shimadzu, Hikaru, Utsuro, Takehito, Kitayama, Daisuke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910884067016704
author Shimadzu, Hikaru
Utsuro, Takehito
Kitayama, Daisuke
author_facet Shimadzu, Hikaru
Utsuro, Takehito
Kitayama, Daisuke
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval-Augmented Simulacra: Generative Agents for Up-to-date and Knowledge-Adaptive Simulations
Shimadzu, Hikaru
Utsuro, Takehito
Kitayama, Daisuke
Computation and Language
Social and Information Networks
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.
title Retrieval-Augmented Simulacra: Generative Agents for Up-to-date and Knowledge-Adaptive Simulations
topic Computation and Language
Social and Information Networks
url https://arxiv.org/abs/2503.14620