MAG-Bot: A Multi-Agent Auditing Framework for Social Bot Detection
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.