# Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program

arXiv: https://arxiv.org/abs/2408.08676 · HTML: https://mlsanity.com/paper/2408.08676/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 6 of 6)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Revisiting Small Batch Training for Deep Neural Networks](https://mlsanity.com/paper/1804.07612/) (2018)
- [AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning](https://mlsanity.com/paper/2102.01386/) (2021)
- [Language Models are Spacecraft Operators](https://mlsanity.com/paper/2404.00413/) (2024)

## Built on by (most cited first, 3 of 3)

- [Towards Agentic AI on Particle Accelerators](https://mlsanity.com/paper/2409.06336/) (2024)
- [Tiny Recursive Control: Iterative Reasoning for Efficient Optimal Control](https://mlsanity.com/paper/2512.16824/) (2025)
- [Autonomous Reasoning for Spacecraft Control: A Large Language Model Framework with Group Relative Policy Optimization](https://mlsanity.com/paper/2601.04334/) (2026)

## Abstract (arXiv)

Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompt. This study explores the use of fine-tuned Large Language Models (LLMs) for autonomous spacecraft control, using the Kerbal Space Program Differential Games suite (KSPDG) as a testing environment. Traditional Reinforcement Learning (RL) approaches face limitations in this domain due to insufficient simulation capabilities and data. By leveraging LLMs, specifically fine-tuning models like GPT-3.5 and LLaMA, we demonstrate how these models can effectively control spacecraft using language-based inputs and outputs. Our approach integrates real-time mission telemetry into textual prompts processed by the LLM, which then generate control actions via an agent. The results open a discussion about the potential of LLMs for space operations beyond their nominal use for text-related tasks. Future work aims to expand this methodology to other space control tasks and evaluate the performance of different LLM families. The code is available at this URL: texttthttps://github.com/ARCLab-MIT/kspdg.