SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911632304635904 |
|---|---|
| author | Meidan, Yair Haller, Omri Moshan, Yulia David, Shahaf Mimran, Dudu Elovici, Yuval Shabtai, Asaf |
| author_facet | Meidan, Yair Haller, Omri Moshan, Yulia David, Shahaf Mimran, Dudu Elovici, Yuval Shabtai, Asaf |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26394 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization Meidan, Yair Haller, Omri Moshan, Yulia David, Shahaf Mimran, Dudu Elovici, Yuval Shabtai, Asaf Cryptography and Security Artificial Intelligence 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. |
| title | SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2604.26394 |