Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bu, Haoran, Zhang, Litian, Zhang, Chuxuan, Liu, Zhanyuan, Pang, Hui, Zhang, Xi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.12512
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917488106668032
author Bu, Haoran
Zhang, Litian
Zhang, Chuxuan
Liu, Zhanyuan
Pang, Hui
Zhang, Xi
author_facet Bu, Haoran
Zhang, Litian
Zhang, Chuxuan
Liu, Zhanyuan
Pang, Hui
Zhang, Xi
contents Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local social interactions, they fail to preserve human-like social network. This is because LLM-based bots are graph-unaware and cannot coordinate over global interactions, which makes those botnets vulnerable to graph neural network (GNN)-based detection. To address this limitation, we propose GraphMind, which equips LLM-driven social bots to explicitly learn and fit human-like social network structures. Building on this foundation, we further construct GraphMind-Botnet, a LLM-driven botnet designed to evaluate the performance of existing social bot detection algorithms. Experiments on datasets derived from GraphMind-Botnet show that both text-based and graph-based detection models show substantially degraded performance in distinguishing. Our results highlight the critical role of social link construction in LLM-driven social network generation, while exposing fundamental weaknesses in existing bot detection mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12512
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents
Bu, Haoran
Zhang, Litian
Zhang, Chuxuan
Liu, Zhanyuan
Pang, Hui
Zhang, Xi
Social and Information Networks
Artificial Intelligence
Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local social interactions, they fail to preserve human-like social network. This is because LLM-based bots are graph-unaware and cannot coordinate over global interactions, which makes those botnets vulnerable to graph neural network (GNN)-based detection. To address this limitation, we propose GraphMind, which equips LLM-driven social bots to explicitly learn and fit human-like social network structures. Building on this foundation, we further construct GraphMind-Botnet, a LLM-driven botnet designed to evaluate the performance of existing social bot detection algorithms. Experiments on datasets derived from GraphMind-Botnet show that both text-based and graph-based detection models show substantially degraded performance in distinguishing. Our results highlight the critical role of social link construction in LLM-driven social network generation, while exposing fundamental weaknesses in existing bot detection mechanisms.
title Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents
topic Social and Information Networks
Artificial Intelligence
url https://arxiv.org/abs/2605.12512