NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimizati...

Authors

Maoqi Liu Beijing University of Posts and Telecommunications
Quan Fang Beijing University of Posts and Telecommunications
Yuhao Wu Beijing University of Posts and Telecommunications
Can Zhao Aviation Data Communication Corporation
Yang Yang Beihang University, School of Electronic and Information Engineering State Key Laboratory of CNS/ATM
Kaiquan Cai Beihang University, School of Electronic and Information Engineering State Key Laboratory of CNS/ATM

DOI:

https://doi.org/10.1609/aaai.v40i1.37043

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 crucial 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.

How to Cite

Liu, M., Fang, Q., Wu, Y., Zhao, C., Yang, Y., & Cai, K. (2026). NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 764–772. https://doi.org/10.1609/aaai.v40i1.37043

Issue

Section

AAAI Technical Track on Application Domains I