用大模型当太空飞船自主操作员，在游戏里拿了第二名。
Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program
- 纯大模型通过提示工程和微调实现自动操控卫星
- 在模拟非合作太空任务中排名第二，表现媲美专业算法
- 开源代码与模型，适合航天自动化与AI Agent研究者
大型语言模型（LLM）作为基于用户文本提示自主行动的智能体，正成为新兴趋势。本文将该理念应用于航天控制领域，探索让大模型参与自主卫星任务决策的可能性。作为第一步，我们开发了一个完全基于大模型的解决方案，用于应对基于Kerbal Space Program游戏引擎的非合作空间操作竞赛（KSPDG）。该方案结合提示工程、少样本提示和微调技术，使大模型在比赛中获得第二名的成绩。据我们所知，这是首个将大模型智能体系统性引入空间研究的工作。项目包含多个开源仓库，代码可在GitHub上获取，训练好的模型与数据集发布于Hugging Face，实验记录与详细结果可通过Weights & Biases查阅。
原文摘要 · Abstract (English)
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 prompts. We intend to apply these concepts to the field of Control in space, enabling LLMs to play a significant role in the decision-making process for autonomous satellite operations. As a first step towards this goal, we have developed a pure LLM-based solution for the Kerbal Space Program Differential Games (KSPDG) challenge, a public software design competition where participants create autonomous agents for maneuvering satellites involved in non-cooperative space operations, running on the KSP game engine. Our approach leverages prompt engineering, few-shot prompting, and fine-tuning techniques to create an effective LLM-based agent that ranked 2nd in the competition. To the best of our knowledge, this work pioneers the integration of LLM agents into space research. The project comprises several open repositories to facilitate replication and further research. The codebase is accessible on \href{https://github.com/ARCLab-MIT/kspdg}{GitHub}, while the trained models and datasets are available on \href{https://huggingface.co/OhhTuRnz}{Hugging Face}. Additionally, experiment tracking and detailed results can be reviewed on \href{https://wandb.ai/carrusk/huggingface}{Weights \& Biases
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。