A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification

2026-09-02

AI Summary

This study addresses the loss of sensitive information caused by long-document truncation and the inefficiency of manual evaluation by proposing CB-MAS, a multi-agent system. Methodologically, it introduces a novel controlled gating channel enhancement mechanism that dynamically weights dual encoders, alongside a blackboard-based adaptive consultation agent that iteratively fuses evidence from document beginnings and endings. This approach overcomes long-text truncation limitations under constant computational budgets while ensuring interpretability through LIME and SHAP techniques. Experimental results demonstrate that CB-MAS achieves 90.72% accuracy, an F1 score of 91.23%, and a sensitivity recall of 92.01%. These metrics significantly outperform baseline models while reducing computational resource consumption by 54%.

Abstract

Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessment is slow, inconsistent, and unscalable. Extending our prior leakage-controlled benchmark, BERT established the top single-encoder baseline (89.14% accuracy, 89.33% F1-score under 5-fold cross-validation on the Strategic 16K corpus). However, transformer baselines suffer from a structural limitation: fixed input length truncation discards evidence beyond the retained window-precisely where sensitive cables tend to be longest. We present Channel-Boosted MAS (CB-MAS) and instantiate it as IC-MAS (Iterative Consultation Multi-Agent System) to solve this without long-context computational costs. A Channel Critic Agent learns document-adaptive trust weights governing Gated Channel Boosting between two first-window encoders, while paired Consultation Agents iteratively exchange belief states to reconcile evidence from the beginning and end of long documents. IC-MAS holds computation constant regardless of document length by reconciling fixed windows in a compact representation space. Ablation studies show critic-controlled Channel Boosting provides the bulk of accuracy gains, while consultation recovers recall without precision collapse. Critic-Controlled Gated Channel Boosting with Max-Pool fusion and Blackboard Adaptive Consultation achieves 90.72% accuracy, 91.23% F1-score, 92.01% sensitive recall, and 90.46% sensitive precision, using about 54% less average computation than a fixed-round baseline. Gains over the single-encoder baseline are statistically significant (McNemar's test, p less than 0.000001; paired t-test). We include LIME/SHAP explainability, multi-agent evaluation, and an honest accounting of limitations.

Problem

• Document Sensitivity Classification
• Input Length Truncation
• Long Documents
• Multi-Agent System

Innovation

• Multi-Agent System
• Channel Boosting
• Iterative Consultation
• Document Sensitivity Classification
• Gated Fusion