让AI航天代理通过语言规则进化，无需改模型就能越用越好
GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
- 用自然语言规则集替代固定提示，动态演化决策策略
- 在对抗性轨道拦截任务中表现优于静态基线，成功率显著提升
- 适合需要持续优化但不能重训练的实时航天控制系统
大型语言模型（LLMs）被提出作为航天器操作的监督代理，但现有方法依赖静态提示，无法在多次执行中改进。本文提出 extsc{GUIDE}，一种非参数化策略改进框架，通过演化结构化的、状态相关的自然语言决策规则手册，实现跨轮次适应，且无需权重更新。轻量级执行模型负责实时控制，离线反思模块则基于历史轨迹更新规则手册。在Kerbal Space Program Differential Games环境中的对抗性轨道拦截任务上评估显示，GUIDE的演化持续优于静态基线。结果表明，LLM代理中的上下文演化可视为在实时闭环航天交互中对结构化决策规则的策略搜索。
原文摘要 · Abstract (English)
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.
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。