End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agent

2026-07-07

AI Summary

Traditional flight planning algorithms struggle to incorporate human operator preferences, hindering the real-world deployment of eVTOLs. This work proposes FRAMe—the first end-to-end large language model (LLM)–based flight planning system—that innovatively integrates a multimodal coaching agent with a retrieval-augmented generation (RAG) memory mechanism to translate natural language instructions into safe, efficient, and preference-aligned flight paths. FRAMe achieves, for the first time, seamless alignment between human intent and autonomous operation in LLM-driven flight planning. Experimental results demonstrate that FRAMe significantly enhances route validity across diverse real-world scenarios, achieving up to 93.8% effectiveness overall (reaching 99% in simpler settings) while consistently improving metrics tied to operator preferences.

Abstract

Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) aircraft deployment. Flight planning traditionally relies on classic algorithms that struggle to incorporate flexible human preferences. We present FRAMe, an End-to-End Large Language Model (LLM) Flight Planning tool with RAG-based Memory and Multi-modal Coach Agent. Our system integrates a planner LLM with a multi-modal coach agent and retrieval augmented generation (RAG)-based memory to generate flight plans that satisfy mission constraints while aligning with human flight operator preferences. We demonstrate the system in a range of real-world-inspired scenarios of varying difficulty levels. Across four LLMs, the full FRAMe system (RAG and coach) yields the highest validity for every planner (up to 93.8% aggregate, 99% on Easy scenarios for the strongest planner) and shifts preference-relevant metrics in the operator-favored direction where the metric has headroom. FRAMe signifies how advanced LLMs can be deployed for human-centric mission planning, translating natural language instructions into safe, efficient, and flexible flight routes. The code is available at: github.com/amin-tabrizian/FlightPlanningLLMs

Problem

• flight planning
• human intent
• autonomous flight
• eVTOL
• human-centric planning

Innovation

• Large Language Model
• Retrieval-Augmented Generation
• Multi-modal Agent
• Flight Planning
• Human-Centric Autonomy