AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection

TL;DR

AGENT-X introduces a zero-shot, multi-agent framework for AI-generated text detection that leverages linguistic guidelines for interpretability and adaptability, outperforming existing methods in accuracy and generalization.

Contribution

It proposes a novel threshold-free, interpretable detection method using specialized linguistic agents and adaptive routing, advancing zero-shot AI-generated text detection.

Findings

Outperforms state-of-the-art methods in accuracy.

Provides robust interpretability and generalization.

Demonstrates effectiveness across diverse datasets.

Abstract

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.