A demand-driven LLM agent with memory and validation detects 40 bugs in 15 real-world projects at 78.43% precision, plus 185 new bugs in high-profile repositories, 174 confirmed or fixed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
A demand-driven LLM agent with memory and validation detects 40 bugs in 15 real-world projects at 78.43% precision, plus 185 new bugs in high-profile repositories, 174 confirmed or fixed.