AI Paper Atlas

Research map / Large language models / Agents, code and math

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

Maoqi Liu, Quan Fang, Yuhao Wu, Can Zhao, Yang Yang, Kaiquan Cai

AAAI 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply iterative SFT+DPO self-evolution with KG-TableRAG and multi-view votingDeepSeek-R1-Distill-Qwen-7B · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.458 -> 0.762Improved
add KG-TableRAG knowledge retrieval (ablation)NOTAM-Evolve · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.721 -> 0.762Improved
add Multi-View inference (rewriting and voting) (ablation)NOTAM-Evolve · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.740 -> 0.762Improved
add both KG-TableRAG and Multi-View (ablation)NOTAM-Evolve · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.690 -> 0.762Improved
more self-evolving iterations (1 to 3) (ablation)NOTAM-Evolve · NOTAM deep parsing, Taxiway subsetaccuracy (%): 64.6 -> 86.8Improved
more self-evolving iterations (1 to 3) (ablation)NOTAM-Evolve · NOTAM deep parsing, Light subsetaccuracy (%): 45 -> 62Improved
plain SFT on the reasoning base modelDeepSeek-R1-Distill-Qwen-7B · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.458 -> 0.212Hurt
NOTAM-Evolve vs plain SFT of Qwen2.5-7B-Instruct7B open models · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.744 -> 0.762Improved
NOTAM-Evolve vs GPT-4o and DeepSeek-R1NOTAM-Evolve · NOTAM deep parsing, average over 4 subsetsexact-match accuracy: 0.762 vs 0.785 and 0.828Mixed
NOTAM-Evolve vs Qwen2.5-7B-Instruct SFT on Area subsetNOTAM-Evolve · NOTAM deep parsing, Area subsetexact-match accuracy: 0.793 -> 0.725Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy