Beyond Text-Intrinsic Features: An Agentic Framework for Evidence-Based AI-Generated Text Detection
Abstract
AbstractWith the rapid advancement of Large Language Models (LLMs), AI-generated text has become increasingly difficult to distinguish from human-authored content, raising serious concerns about online misinformation and academic integrity. Although plenty of methods have been proposed, they often suffer from high false positives on formal or highly structured human-written texts. Moreover, while external contextual information can provide valuable signals for verification, it remains largely underutilized in existing detection frameworks. In this paper, we propose an agentic framework driven by LLM for AI-generated text detection that integrates multiple machine learning (ML) detectors with an online search module to retrieve and leverage external evidence. Evaluated on a diverse real-world dataset spanning four distinct sources, our agent significantly outperforms standalone detectors, achieving an overall accuracy of 93.90%. We show that online search acts as an effective error-correction mechanism under detector conflict and incorrect agreement, improving accuracy by 10.81% and 90.91%, respectively. We further conduct a failure analysis, identifying key limitations and providing directions for future research.