mlsanityData to 13 Oct 2026

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

arXiv 2606.16987 ↗First posted 15 Jun 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 9 of its 37 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

9 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Agentic Large Language Models, a survey29 Mar

Other references · 8

  1. 2025Qwen3 Technical Reportcited by 8,510
  2. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,319
  3. 2025HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Applicationcited by 5
  4. 2025Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Modelscited by 4
  5. 2026Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoningcited by 4
  6. 2024Benchmarking Harmonized Tariff Schedule Classification Modelscited by 3
  7. 2025ATLAS: Benchmarking and Adapting LLMs for Global Trade via Harmonized Tariff Code Classificationcited by 3
  8. 2023Explainable Product Classification for Customscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Deterministic Agentic Workflow for HS Tariff Classification: Multi-Dimensional Rule Reasoning with Interpretable Decisions
  2. 2026Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification
  3. 2024LLM-Based Robust Product Classification in Commerce and Compliance
  4. 2026Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance
  5. 2025VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language
  6. 2026Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support
  7. 2026Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks
  8. 2026QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code