VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support

arXiv cs.AI / 3/18/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

VIGIL is an edge-extended agentic AI system that deploys desktop-resident agents to perform situated diagnosis, retrieval over enterprise knowledge, and policy-governed remediation on user devices with explicit consent and end-to-end observability.
In a 10-week pilot across 100 resource-constrained endpoints, VIGIL reduced interaction rounds by 39% and achieved at least 4× faster diagnosis.
The system enables self-service resolution in 82% of matched cases, with users reporting excellent usability, high trust, and low cognitive workload, and transparency identified as critical for trust.
On-device diagnosis remains valuable even when the knowledge base coverage is limited, supporting safety and observability for fleet-wide continuous improvement.
The work establishes foundations for scalable, enterprise-wide deployment of agentic AI with strong safety, observability, and user-consent considerations.

Abstract

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.