MAS-SZZ uses multi-agent collaboration and structured prompting to identify vulnerability-inducing commits, achieving up to 65.22% F1-score gains over prior SZZ algorithms.
IEEE Trans
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
-
MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification
MAS-SZZ uses multi-agent collaboration and structured prompting to identify vulnerability-inducing commits, achieving up to 65.22% F1-score gains over prior SZZ algorithms.