NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation

2025-11-11

AI Summary

NOTAMs’ terse and ambiguous language impedes both human and automated interpretation, with existing systems largely confined to shallow syntactic parsing—insufficient for safety-critical flight decision support. This paper proposes a knowledge-guided, self-evolving deep parsing framework that integrates large language models (LLMs), knowledge graph–enhanced retrieval, dynamic knowledge grounding, and pattern-driven reasoning. Through a closed-loop learning mechanism, the framework enables autonomous LLM refinement, substantially reducing reliance on manually annotated data. Evaluated on a dataset of over 10,000 expert-annotated NOTAMs, our approach achieves a structured interpretation accuracy of 89.6%, representing a 30.4-percentage-point improvement over the base LLM and establishing a new state-of-the-art. The framework delivers a rigorous, verifiable, and operationally deployable solution for automated understanding of aviation safety–critical NOTAM information.

Technology Category

• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Accurate interpretation of Notices to Airmen (NOTAMs) is critical for aviation safety, yet their condensed and cryptic language poses significant challenges to both manual and automated processing. Existing automated systems are typically limited to shallow parsing, failing to extract the actionable intelligence needed for operational decisions. We formalize the complete interpretation task as deep parsing, a dual-reasoning challenge requiring both dynamic knowledge grounding (linking the NOTAM to evolving real-world aeronautical data) and schema-based inference (applying static domain rules to deduce operational status). To tackle this challenge, we propose NOTAM-Evolve, a self-evolving framework that enables a large language model (LLM) to autonomously master complex NOTAM interpretation. Leveraging a knowledge graph-enhanced retrieval module for data grounding, the framework introduces a closed-loop learning process where the LLM progressively improves from its own outputs, minimizing the need for extensive human-annotated reasoning traces. In conjunction with this framework, we introduce a new benchmark dataset of 10,000 expert-annotated NOTAMs. Our experiments demonstrate that NOTAM-Evolve achieves a 30.4% absolute accuracy improvement over the base LLM, establishing a new state of the art on the task of structured NOTAM interpretation.

Problem

• Interpreting cryptic aviation NOTAMs for flight safety decisions
• Overcoming shallow parsing limitations in automated NOTAM systems
• Addressing dual-reasoning challenges in dynamic knowledge grounding

Innovation

• Knowledge graph-enhanced retrieval for data grounding
• Closed-loop learning process for autonomous improvement
• Self-evolving framework minimizing human annotation needs