作者位次 #2/10NeurIPS 2026Poster
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Gabriel Orlanski · Devjeet R Roy · Alexander Yun · Changho Shin · Alex Gu · Albert Ge · Dyah Adila · Nicholas Roberts · Frederic Sala · Aws Albarghouthi