GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908964695834624 |
|---|---|
| author | Carrasco, Alejandro Storey-Matsutani, Mariko Rodriguez-Fernandez, Victor Linares, Richard |
| author_facet | Carrasco, Alejandro Storey-Matsutani, Mariko Rodriguez-Fernandez, Victor Linares, Richard |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27306 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations Carrasco, Alejandro Storey-Matsutani, Mariko Rodriguez-Fernandez, Victor Linares, Richard Multiagent Systems Artificial Intelligence Systems and Control 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. |
| title | GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations |
| topic | Multiagent Systems Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2603.27306 |