AI RESEARCH
SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents
arXiv CS.AI
•
ArXi:2604.12040v1 Announce Type: cross We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with expert-validated ground truth, SIR-Bench measures not only whether agents reach correct triage decisions, but whether they discover novel evidence through active investigation.