VAST: Compiling Grounded Vulnerability Scenarios into Verifiable, Multi-Step Environments for Evaluating LLM Red-Team Agents

arXiv:2611.19465 · cs.CR, cs.AI · Submitted 2026-11-14 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-11-14

Updated: 2026-11-14

Related papers