ArXiv TLDR

SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization

🐦 Tweet
2604.26394

Yair Meidan, Omri Haller, Yulia Moshan, Shahaf David, Dudu Mimran + 2 more

cs.CRcs.AI

TLDR

SecMate is a multi-agent AI for cybersecurity troubleshooting that uses device, user, and service context to achieve over 90% resolution accuracy.

Key contributions

  • Introduces SecMate, a multi-agent VCA for cybersecurity troubleshooting with tri-context personalization.
  • Achieved over 90% correct resolutions by integrating device-level diagnostics, up from 50% for LLM-only.
  • Proactive, context-aware recommender showed high relevance (MRR@1=0.75) and reduced user burden.
  • Participants showed strong willingness to substitute human IT support, demonstrating practical value.

Why it matters

This paper introduces SecMate, a significant advancement in AI-driven cybersecurity support. By integrating deep contextual understanding, it dramatically improves troubleshooting accuracy and user experience. This work paves the way for more effective and cost-efficient virtual IT assistance.

Original 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.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.