# GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations

arXiv: https://arxiv.org/abs/2603.27306 · HTML: https://mlsanity.com/paper/2603.27306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Controlled Self-Evolution for Algorithmic Code Optimization](https://mlsanity.com/paper/2601.07348/) (2026)
- [Language Models are Spacecraft Operators](https://mlsanity.com/paper/2404.00413/) (2024)
- [Visual Language Models as Operator Agents in the Space Domain](https://mlsanity.com/paper/2501.07802/) (2025)
- [Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program](https://mlsanity.com/paper/2505.19896/) (2025)
- [Brewing Knowledge in Context: Distillation Perspectives on In-Context Learning](https://mlsanity.com/paper/2506.11516/) (2025)
- [WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents](https://mlsanity.com/paper/2601.08158/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce textscGUIDE, a non-parametric policy improvement framework that enables cross-episode adaptation without weight updates by evolving a structured, state-conditioned playbook of natural-language decision rules. A lightweight acting model performs real-time control, while offline reflection updates the playbook from prior trajectories. Evaluated on an adversarial orbital interception task in the Kerbal Space Program Differential Games environment, GUIDE's evolution consistently outperforms static baselines. Results indicate that context evolution in LLM agents functions as policy search over structured decision rules in real-time closed-loop spacecraft interaction.