GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
The integration of Large Language Models (LLMs) into robotic control, including drones, has the potential to revolutionize autonomous systems. Research studies have demonstrated that LLMs can be leveraged to support robotic operations. However, when facing tasks with complex reasoning, concerns and challenges are raised about the reliability of solutions produced by LLMs. In this paper, we propose a prompt framework with enhanced reasoning to enable reliable LLM-driven control for drones. Our framework consists of novel technical components designed using Guidelines, Skill APIs, Constraints, and Examples, namely GSCE. GSCE is featured by its reliable and constraint-compliant code generation. We performed thorough experiments using GSCE for the control of drones with a wide level of task complexities. Our experiment results demonstrate that GSCE can significantly improve task success rates and completeness compared to baseline approaches, highlighting its potential for reliable LLM-driven autonomous drone systems.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 1 of its 38 references that are in the map. First posted on arXiv 18 Feb 2025.
Builds on
1 of 38 references.
References · 1
- 2023TypeFly: Flying Drones with Large Language Modelcited by 23
Built on by
Citing papers per year: 2025: 4; 2026: 3.
7 papers.
- 2025GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamicscited by 14
- 2026Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Dronescited by 4
- 2025A Hierarchical Agentic Framework for Autonomous Drone-Based Visual Inspectioncited by 3
- 2025CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarioscited by 2
- 2026End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agentcited by 1
- 2025Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic Reasoningcited by 0
- 2026AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDKcited by 0
- 2026End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agent8 Jul 2026
- 2026Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones5 May 2026
- 2026AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK15 Mar 2026
- 2025A Hierarchical Agentic Framework for Autonomous Drone-Based Visual Inspection30 Sep 2025
- 2025GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics16 Jun 2025
- 2025Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic Reasoning5 Jun 2025
- 2025CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios30 Apr 2025
Similar, not cited
Close in wording, no citation either way
- 2026An LLM-Agnostic, MAVLink-Based Drone Command and Control Interface and Agentic Harness Using the Model Context Protocol
- 2025Large Language Model-Driven Closed-Loop UAV Operation with Semantic Observations
- 2025General-Purpose Aerial Intelligent Agents Empowered by Large Language Models
- 2026Ro-SLM: Onboard Small Language Models for Robot Task Planning and Operation Code Generation
- 2025LLM-Driven Self-Refinement for Embodied Drone Task Planning
- 2026SAGE-LLM: Towards Safe and Generalizable LLM Controller with Fuzzy-CBF Verification and Graph-Structured Knowledge Retrieval for UAV Decision
- 2024Defining and Evaluating Physical Safety for Large Language Models
- 2025AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs