Vulnerability Detection on curated CVE
44Detection Accuracyrole-based agentic workflow (Workflow 1)
Evaluation Results
| Method | Links | |
|---|---|---|
| role-based agentic workflow (Workflow 1)CodeQL=without CodeQL, Planner=included2026.06 | 44 | |
| OpenAI GPT-5.5.Setting=Baseline2026.06 | 44 | |
| role-based agentic workflow (Workflow 2)CodeQL=with CodeQL, Planner=included2026.06 | 31 | |
| role-based agentic workflow (Workflow 1)CodeQL=without CodeQL, Planner=without Planner2026.06 | 25 | |
| role-based agentic workflow (Workflow 2)CodeQL=with CodeQL, Planner=without Planner2026.06 | 19 |