xianyu-sheng

xianyu-sheng/SmartBench

Evidence-grounded code diagnosis with structural parsing, retrieval, and multi-agent review

1 stars 1 forks 1 watchers Python MIT License
benchmark code-analysis code-quality debate evidence-checking llm multi-agent python rag static-analysis verification
View on GitHub
2 Open Issues Need Help Last updated: Jul 30, 2026

Open Issues Need Help

View All on GitHub
No negative corpus: false-positive rate is unmeasured 6 days ago
help wanted roadmap measurement
xianyu-sheng/SmartBench
1

Evidence-grounded code diagnosis with structural parsing, retrieval, and multi-agent review

Python
#benchmark#code-analysis#code-quality#debate#evidence-checking#llm#multi-agent#python#rag#static-analysis#verification
No executable conformance suite for the documented new-frontend acceptance criteria 6 days ago
help wanted roadmap language-layer
xianyu-sheng/SmartBench
1

Evidence-grounded code diagnosis with structural parsing, retrieval, and multi-agent review

Python
#benchmark#code-analysis#code-quality#debate#evidence-checking#llm#multi-agent#python#rag#static-analysis#verification