Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

ArXi:2605.12512v1 Announce Type: cross 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.