Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification

2026-06-15

AI Summary

This study addresses the challenge of accurately classifying ten-digit Harmonized Tariff Schedule (HTS) codes in the Canadian context, where ambiguous product descriptions and complex, evolving classification rules hinder precise categorization. To tackle this issue, the authors propose a multi-agent large language model framework that integrates semantic retrieval, hierarchical voting, consensus validation, and human-in-the-loop collaboration. The framework incorporates uncertainty-aware mechanisms and compliance-oriented traceability to ensure explainable and regulation-compliant classification outcomes. Evaluated on a dataset of 3,300 expert-annotated entries, the approach demonstrates significant improvements in accuracy, reliability, and interpretability for fine-grained HTS code assignment, offering a novel paradigm for intelligent customs declaration under stringent regulatory requirements.

Abstract

Accurate Harmonized Tariff Schedule (HTS) code classification is essential for customs clearance, duty assessment, trade statistics, and regulatory compliance in maritime logistics. However, exact HTS classification remains challenging because product descriptions are often short, incomplete, or ambiguous, while correct classification depends on hierarchical tariff structures, legal notes, and jurisdiction-specific rules. This paper proposes an agentic large language model (LLM) framework for Canadian 10-digit HTS code classification in smart-port and maritime logistics environments. The framework integrates multi-agent information retrieval, semantic retrieval over official tariff documents, evidence-grounded reasoning, consensus-based validation, element-wise voting across hierarchical code components, confidence estimation, and human-in-the-loop escalation. We evaluate the framework on a private dataset of 3,300 domain-expert-labeled product records collected from logistics and delivery contexts. Experimental results show that exact 10-digit classification remains difficult even for advanced LLMs, with performance decreasing from coarse chapter-level prediction to fine-grained tariff and statistical suffix assignment. These findings demonstrate the need for evidence-grounded, uncertainty-aware, and human-centered classification workflows rather than fully autonomous single-step prediction. The proposed framework supports more interpretable, accountable, and compliance-oriented HTS classification for maritime logistics and smart-port operations. Our code is available at https://github.com/Analytics-Everywhere-Lab/hts.

Problem

• Harmonized Tariff Schedule
• HTS code classification
• maritime logistics
• smart-port
• customs compliance

Innovation

• agentic LLM
• consensus-based validation
• HTS code classification
• evidence-grounded reasoning
• human-in-the-loop