SEC-bench Pro benchmark with 183 real vulnerabilities shows frontier LLM coding agents achieve at most 38.8% success on SpiderMonkey and 32% on V8.
A Dual-Loop Agent Framework for Automated Vulnerability Reproduction.arXiv preprint arXiv:2602.05721,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
SEC-bench Pro benchmark with 183 real vulnerabilities shows frontier LLM coding agents achieve at most 38.8% success on SpiderMonkey and 32% on V8.