Detecting machine-generated text (MGT) from contemporary Large Language Models (LLMs) is increasingly crucial amid risks like disinformation and threats to academic integrity. Existing zero-shot detection paradigms, despite their practicality, often exhibit significant deficiencies. Key challenges include: (1) superficial analyses focused on limited textual attributes, and (2) a lack of investigation into consistency across linguistic dimensions such as style, semantics, and logic. To address these challenges, we introduce the Collaborative Adversarial Multi-agent Framework (CAMF), a novel architecture using multiple LLM-based agents. CAMF employs specialized agents in a synergistic three-phase process: Multi-dimensional Linguistic Feature Extraction, Adversarial Consistency Probing, and Synthesized Judgment Aggregation. This structured collaborative-adversarial process enables a deep analysis of subtle, cross-dimensional textual incongruities indicative of non-human origin. Empirical evaluations demonstrate CAMF's significant superiority over state-of-the-art zero-shot MGT detection techniques.
Wang et al. (Sat,) studied this question.