A decoupled evaluation framework shows LLM penetration agents reach 90% exploitation success with ground-truth context but only 50% reconnaissance recall due to telemetry parsing failures across 50 vulnerabilities.
Detecting and correcting hallucinations in llm-generated code via static knowledge validation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Post-release defects concentrate in older, frequently modified high-churn components and require longer and more complex fixes than pre-release defects.
citing papers explorer
-
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
A decoupled evaluation framework shows LLM penetration agents reach 90% exploitation success with ground-truth context but only 50% reconnaissance recall due to telemetry parsing failures across 50 vulnerabilities.
-
What Makes Software Bugs Escape Testing? Evidence from a Large-Scale Empirical Study
Post-release defects concentrate in older, frequently modified high-churn components and require longer and more complex fixes than pre-release defects.