@article{slopcodebenchbenchmarkinghowcodingagents, title = {SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks}, author = {Gabriel Orlanski and Devjeet Roy and Alexander Yun and Changho Shin and Alex Gu and Albert Ge and Dyah Adila and Nicholas Roberts and Frederic Sala and Aws Albarghouthi}, year = {2026}, eprint = {2603.24755}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.24755}, }