让电脑自带AI助手，本地诊断故障，提升企业运维效率。
VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support
- 在用户设备上部署本地AI代理，实现就地诊断与修复。
- 试点中交互次数减少39%，诊断速度提升4倍，82%问题可自助解决。
- 适合关注隐私安全、希望降低运维负担的企业用户。
企业IT支持受限于设备异构性、政策动态变化以及难以集中处理的长尾故障。我们提出VIGIL，一种面向企业IT支持的边缘扩展型智能体系统，通过部署在桌面端的智能体，在用户明确授权和端到端可观测的前提下，直接在用户设备上执行情境化诊断、企业知识检索及受策略约束的修复操作。在100台资源受限终端上为期10周的试点运行表明，VIGIL将交互轮次减少39%，诊断速度至少提升4倍，并在82%的匹配案例中支持自助修复。用户在四项验证量表中均表现出优异的可用性、高信任度和低认知负荷，定性反馈强调透明性对建立信任至关重要。值得注意的是，当无历史匹配时，用户评分反而更高，表明本地诊断本身具有独立价值，不依赖知识库覆盖度。该试点为全量部署奠定了安全与可观测性基础。
原文摘要 · Abstract (English)
Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents to perform situated diagnosis, retrieval over enterprise knowledge, and policy-governed remediation directly on user devices with explicit consent and end-to-end observability. In a 10-week pilot of VIGIL's operational loop on 100 resource-constrained endpoints, VIGIL reduces interaction rounds by 39%, achieves at least 4 times faster diagnosis, and supports self-service resolution in 82% of matched cases. Users report excellent usability, high trust, and low cognitive workload across four validated instruments, with qualitative feedback highlighting transparency as critical for trust. Notably, users rated the system higher when no historical matches were available, suggesting on-device diagnosis provides value independent of knowledge base coverage. This pilot establishes safety and observability foundations for fleet-wide continuous improvement.
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。