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

Alejandro Carrasco, Mariko Storey-Matsutani, Victor Rodriguez-Fernandez, Richard Linares

Keywords: large language models, in-context learning, non-parametric policy improvement, context evolution, spacecraft autonomy, closed-loop control, adversarial multi-agent systems, sequential decision making, offline reflection, real-time control

TL;DR: GUIDE evolves a structured natural-language playbook of state-conditioned decision rules across episodes, enabling real-time LLM policy improvement without weight updates — outperforming static baselines on adversarial orbital interception tasks.

Abstract: 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 \textsc{GUIDE}, 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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 18