Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMate, a multi-agent VCA for cybersecurity troubleshooting that integrates device, user, and service specificity from conversational and device-level signals. Device specificity is provided by a lightweight local diagnostic utility, while user specificity relies on implicit proficiency inference and profile-aware troubleshooting. Service specificity is achieved through a proactive, context-aware recommender. We evaluate SecMate in a controlled study with 144 participants and 711 conversations. Device-level evidence increased correct resolutions from about 50% to over 90% relative to an LLM-only baseline, while step-by-step guidance improved pleasantness and reduced user burden. The recommender achieved high relevance (MRR@1=0.75), and participants showed strong willingness to substitute human IT support at costs well below human benchmarks. We release the full code base and a richly annotated dataset to support reproducible research on adaptive VCAs.

翻译：大型语言模型与智能体框架的最新进展使得虚拟客户助手（VCA）能够处理复杂支持任务。我们提出SecMate——一种面向网络安全故障排除的多智能体VCA，该模型从对话与设备级信号中整合了设备、用户及服务的特异性。设备特异性通过轻量级本地诊断工具实现；用户特异性则依赖隐性能力推断与用户画像感知的故障排除方法；服务特异性通过主动式上下文感知推荐器达成。我们在包含144名参与者与711段对话的受控实验中评估了SecMate。与仅使用大语言模型的基线相比，设备级证据将问题正确解决率从约50%提升至超90%，分步式指导显著提升了体验愉悦度并降低了用户负担。推荐器表现出高相关性（MRR@1=0.75），且参与者表现出在显著低于人力成本的情况下替代人工IT支持的强烈意愿。我们已开源完整代码库与丰富标注数据集，以支持自适应VCA的可复现研究。