SafeLink-Agent：面向动态Starlink网络的自适应码率控制器的智能体式维护框架
SafeLink-Agent: Agentic Maintenance for Adaptive Bitrate Controllers over Dynamic Starlink Networks
浏览论文内容
中文总结 AI 辅助
该研究针对动态Starlink网络下ABR控制器难以适配复杂配置的问题，提出SafeLink-Agent框架，通过LLM智能体生成并验证补丁，显著降低了不同类型ABR控制器的严重会话比例，提升了流媒体鲁棒性。
中文摘要 AI 辅助
以Starlink为代表的低轨（LEO）卫星宽带，使高分辨率视频流媒体在固定地面覆盖范围之外也成为可能。然而，Starlink接入链路会随时间和区域变化，使自适应码率（ABR）流媒体面临不断变化的吞吐量尾部、延迟、波动性及切换条件。现有ABR控制器通常针对特定网络条件设计、调优或训练，难以应对新出现的复杂Starlink配置。本文提出SafeLink-Agent，一种面向动态Starlink网络的ABR控制器的智能体式维护框架。SafeLink-Agent汇总已暴露的故障，采用基于大语言模型（LLM）的智能体补丁提议器生成候选补丁，同时通过重放验证确定每个补丁是否可安全提交。该框架在同一维护工作流下同时支持基于规则的控制器和学习型控制器。在真实Starlink网络上的实验表明，SafeLink-Agent将RobustMPC的严重会话比例从2.60%降至0.40%，并在滚动维护中将累计严重会话从45次减少至7次；对于学习型控制器，经验证的自适应审计将平均严重会话比例从39.01%降至9.79%。这些结果表明，智能体式维护可提升动态Starlink接入条件下ABR的鲁棒性。
英文摘要
Low Earth orbit (LEO) satellite broadband, represented by Starlink, is making high-resolution video streaming feasible beyond fixed terrestrial coverage. However, Starlink access links change across time and regions, exposing adaptive bitrate (ABR) streaming to shifting throughput tails, latency, volatility, and handover conditions. Existing ABR controllers are usually designed, tuned, or trained for specific network conditions, making it difficult to handle newly exposed hard Starlink profiles. This paper proposes SafeLink-Agent, an agentic maintenance framework for ABR controllers over dynamic Starlink networks. SafeLink-Agent summarizes exposed failures and uses a large language model (LLM)-based agentic patch proposer to generate candidate patches, while replay verification determines whether each patch can be safely committed. The framework supports both rule-based controllers and learned controllers under the same maintenance workflow. Experiments on real Starlink networks show that SafeLink-Agent reduces the severe-session ratio of RobustMPC from 2.60% to 0.40% and reduces cumulative severe sessions from 45 to 7 in rolling maintenance. For learned controllers, verified adaptive auditing lowers the average severe-session ratio from 39.01% to 9.79%. These results demonstrate that agentic maintenance can improve ABR robustness under dynamic Starlink access conditions.
