Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones

Su, Qingran; Li, Xingze; Ren, Yuming; Fu, Bing; Hu, Chunming; Yin, Yongfeng

doi:10.3390/drones9110780

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones

by

Qingran Su

¹

,

Xingze Li

^2,*,

Yuming Ren

²,

Bing Fu

²,

Chunming Hu

² and

Yongfeng Yin

^2,*

¹

School of Computer Science and Engineering, Beihang University, Beijing 100191, China

²

School of Software, Beihang University, Beijing 100191, China

^*

Authors to whom correspondence should be addressed.

Drones 2025, 9(11), 780; https://doi.org/10.3390/drones9110780 (registering DOI)

Submission received: 11 August 2025 / Revised: 31 October 2025 / Accepted: 5 November 2025 / Published: 9 November 2025

(This article belongs to the Special Issue Design and Flight Control of Low-Speed Near-Space Unmanned Systems)

Download Review Reports Versions Notes

Abstract

As the application of high-altitude solar drones expands, ensuring their safety is paramount. Traditional safety modeling, which relies on manual expert analysis, struggles to keep pace with rapid development cycles. While Large Language Models (LLMs) offer a path to automation, state-of-the-art reasoning frameworks like Graph of Thoughts (GoT) are too generic, lacking the domain-specific knowledge required for effective application. To address this gap, we introduce K-EGoT, a framework that grounds LLM reasoning in a verifiable, domain-specific knowledge base. Our method introduces a “Safety Rationale”—a mandatory, auditable link between LLM-generated model extensions and expert-curated safety principles. We then train a specialized model using a novel “thought process alignment” strategy, applying Direct Preference Optimization (DPO) to the quality of these rationales to ensure the model’sreasoning aligns with expert logic. On a high-fidelity dataset for the flight control–energy coupling problem, our 7B K-EGoT model achieved a Safety Extension Score (SES) of 92.7, significantly outperforming the 84.7 score from standard GoT prompting. Our work delivers a reliable and auditable solution for automated safety modeling for this critical class of drones.

Keywords: high-altitude solar drones; flight control-energy coupling; safety modeling; safety analysis

Share and Cite

MDPI and ACS Style

Su, Q.; Li, X.; Ren, Y.; Fu, B.; Hu, C.; Yin, Y. Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones. Drones 2025, 9, 780. https://doi.org/10.3390/drones9110780

AMA Style

Su Q, Li X, Ren Y, Fu B, Hu C, Yin Y. Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones. Drones. 2025; 9(11):780. https://doi.org/10.3390/drones9110780

Chicago/Turabian Style

Su, Qingran, Xingze Li, Yuming Ren, Bing Fu, Chunming Hu, and Yongfeng Yin. 2025. "Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones" Drones 9, no. 11: 780. https://doi.org/10.3390/drones9110780

APA Style

Su, Q., Li, X., Ren, Y., Fu, B., Hu, C., & Yin, Y. (2025). Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones. Drones, 9(11), 780. https://doi.org/10.3390/drones9110780

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Thinking like an Expert: Aligning LLM Thought Processes for Automated Safety Modeling of High-Altitude Solar Drones

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI