A multi-agent, multi-stage LLM framework (VIC-RAGENT) outperforms direct prompting, CoT, and CodeAgent baselines on F1-score for detecting vulnerability-inducing commits on the V-SZZ dataset.
In: 2014 Software Evolution Week - IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE)
1 Pith paper cite this work, alongside 50 external citations. Polarity classification is still indexing.
1
Pith paper citing it
50
external citations · external index
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detecting Vulnerability-Inducing Commits via Multi-Stage Reasoning with LLM-Based Agents
A multi-agent, multi-stage LLM framework (VIC-RAGENT) outperforms direct prompting, CoT, and CodeAgent baselines on F1-score for detecting vulnerability-inducing commits on the V-SZZ dataset.