让大模型操作命令更安全，通过执行反馈持续优化动作选择与覆盖
Agentic Router: An Execution-Grounded Continual Learning Approach With Memory
- 双路径架构：生成多动作并预测执行后果，再基于收益与风险重排选择
- 实验显示可行动作覆盖率和首次执行成功率均显著提升，最高达92.3%
- 适合需要高可靠性的网络自动化场景，如数据中心运维
大型语言模型（LLM）代理为基于命令行的网络运维提供了前景广阔的接口，但一个看似合理的命令在执行后仍可能失败或引入操作风险。现有方法主要关注命令生成或最终配置正确性，未利用执行后的经验来共同提升候选动作覆盖范围与动作选择质量。本文提出一种执行接地的双路径、后果感知代理，用于基于CLI的SONiC运维。该代理生成多个完整操作动作，预测其执行后果，并通过收益与风险感知的重排序选择最终动作。提案路径将可复用的操作经验抽象为可检索的指导信息，以不修改原始提案LLM的方式提升可行动作覆盖；选择路径则通过会话级LoRA更新，利用真实的SSH反馈自适应改进后果预测器。在多种Qwen3提案模型下的多轮SONiC运维会话实验表明，该框架显著提升了可行动作覆盖率和首屏执行成功率，且两条适应路径带来互补性增益。
原文摘要 · Abstract (English)
Large language model (LLM) agents provide a promising interface for command-line-based network operations, but a plausible command may still fail or introduce operational risk after execution. Existing approaches mainly focus on command generation or final configuration correctness, and do not use execution-grounded experience to jointly improve candidate coverage and action selection. We propose an execution-grounded dual-path consequence-aware agent for CLI-based SONiC operations, which generates multiple complete actions, predicts their execution consequences, and selects the final action through utility- and risk-aware reranking. The proposal-side path abstracts reusable operational lessons into retrievable guidance to improve feasible-action coverage without modifying the proposal LLM, while the selection-side path adapts the consequence predictor through session-level LoRA updates using real SSH feedback to improve conditional selection quality. Experiments over multi-turn SONiC operation sessions with different Qwen3 proposal models show that the framework improves feasible-action coverage and top-1 execution success, and that the two adaptation paths provide complementary gains over 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。