MAG-Bot：一种用于社交机器人检测的多智能体审计框架
MAG-Bot: A Multi-Agent Auditing Framework for Social Bot Detection
浏览论文内容
中文总结 AI 辅助
本研究提出基于LangGraph的多智能体框架MAG-Bot，用于社交机器人检测，通过角色约束的证据分解修正单LLM审计的盲点，在TwiBot-22测试集上显著提升了检测的准确率、召回率与F1值。
中文摘要 AI 辅助
本文将社交机器人检测研究视为基于档案的账户审计，结合大语言模型与图结构化多智能体框架。我们从TwiBot-22重构图数据为账户级记录，整合个人资料元数据、行为统计、上下文线索及近期推文。我们对比了传统基于特征的基线、直接零样本单LLM审计器，以及基于LangGraph的多智能体系统MAG-Bot，得出三项发现：第一，零样本单LLM审计可行，但存在与召回率相关的盲点，尤其针对稀疏、弱依据账户及连贯的角色绑定 persona；第二，角色约束的多智能体分解大幅优于单LLM：在含585个账户的测试拆分中，MAG-Bot将准确率从0.5846提升至0.7017，召回率从0.5986提升至0.8289，F1值从0.6747提升至0.8028；第三，该提升主要源于对行为和上下文专家的诊断驱动强化，而非聚合技巧或事后辩论。因此，多智能体LLM审计的核心价值在于角色约束的证据分解与盲点修正。
英文摘要
This paper studies social bot detection as dossier-based account auditing with large language models and a graph-structured multi-agent framework. From TwiBot-22, we reconstruct graph data into account-level records combining profile metadata, behavioral statistics, contextual cues, and recent tweets. We compare conventional feature-based baselines, a direct zero-shot Single-LLM auditor, and MAG-Bot, a LangGraph-based multi-agent system. Three findings emerge. First, zero-shot Single-LLM auditing is feasible but has recall-related blind spots, especially on sparse, weakly grounded accounts and coherent role-bound personas. Second, role-constrained multi-agent decomposition substantially improves over Single-LLM: on the 585-account test split, MAG-Bot improves accuracy from 0.5846 to 0.7017, recall from 0.5986 to 0.8289, and F1 from 0.6747 to 0.8028. Third, the gain comes mainly from diagnosis-driven strengthening of the behavioral and contextual specialists, not aggregation tricks or post-hoc debate. Multi-agent LLM auditing therefore derives its main value from role-constrained evidence decomposition and blind-spot correction.
