Abstract: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.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.26394 [cs.CR] |
| (or arXiv:2604.26394v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26394 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Asaf Shabtai [view email]
[v1]
Wed, 29 Apr 2026 08:04:16 UTC (2,657 KB)