CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
CheckerBench measures whether coding agents can write working static-analysis checkers across 300 CVE-based tasks.
1 stories, newest first · one card per story
CheckerBench measures whether coding agents can write working static-analysis checkers across 300 CVE-based tasks.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views