LongWoF-Bench: Evaluating EvoMap Genes for Long Workflows

EvoMapAI · hf · 2026-08-25

EvoMapAI released LongWoF-Bench to evaluate EvoMap genes on verifiable long-workflow tasks. EvoMap externalizes verified execution experience into reusable structured "Genes," improving task completion rates and reducing token costs across diverse models.

Original post →

More from coding & agent

coding & agent channel →