AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection
This addresses the need for more adaptable and interpretable detection tools in AI content moderation, though it builds incrementally on existing linguistic approaches.
The paper tackled the problem of AI-generated text detection by proposing AGENT-X, a zero-shot multi-agent framework that uses linguistic guidelines to avoid reliance on large annotated datasets and threshold tuning, achieving substantial improvements in accuracy, interpretability, and generalization over state-of-the-art methods.
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.