无需标注数据和阈值，用多专家系统自动识别AI生成文本
AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection
- 构建三维度语言专家网络，分别评估语义、风格和结构特征
- 在多个数据集上超越现有方法，在零样本场景下准确率超10个百分点
- 自适应路由机制按文本特点选最优检测规则，适合高可靠性场景
现有AI生成文本检测方法严重依赖大规模标注数据和外部阈值调优，限制了可解释性、适应性和零样本效果。为此，我们提出AGENT-X，一种基于经典修辞学与系统功能语言学的零样本多智能体框架。具体而言，将检测准则划分为语义、风格和结构三个维度，由专用语言智能体独立评估，并通过语义引导实现显式推理与鲁棒校准置信度。元智能体采用置信度感知聚合整合各评估结果，实现无阈值、可解释的分类。此外，自适应混合智能体路由器根据推断的文本特征动态选择检测准则。在多样化数据集上的实验表明，AGENT-X在准确性、可解释性和泛化能力上均显著优于最先进的监督与零样本方法。
原文摘要 · Abstract (English)
Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose AGENT-X, a zero-shot multi-agent framework informed by classical rhetoric and systemic functional linguistics. Specifically, we organize detection guidelines into semantic, stylistic, and structural dimensions, each independently evaluated by specialized linguistic agents that provide explicit reasoning and robust calibrated confidence via semantic steering. A meta agent integrates these assessments through confidence-aware aggregation, enabling threshold-free, interpretable classification. Additionally, an adaptive Mixture-of-Agent router dynamically selects guidelines based on inferred textual characteristics. Experiments on diverse datasets demonstrate that AGENT-X substantially surpasses state-of-the-art supervised and zero-shot approaches in accuracy, interpretability, and generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。