{"ID":2881608,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11933","arxiv_id":"2508.11933","title":"CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection","abstract":"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 \\textbf{C}ollaborative \\textbf{A}dversarial \\textbf{M}ulti-agent \\textbf{F}ramework (\\textbf{CAMF}), a novel architecture using multiple LLM-based agents. CAMF employs specialized agents in a synergistic three-phase process: \\emph{Multi-dimensional Linguistic Feature Extraction}, \\emph{Adversarial Consistency Probing}, and \\emph{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.","short_abstract":"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) superfic...","url_abs":"https://arxiv.org/abs/2508.11933","url_pdf":"https://arxiv.org/pdf/2508.11933v1","authors":"[\"Yue Wang\",\"Liesheng Wei\",\"Yuxiang Wang\"]","published":"2025-08-16T06:25:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}