@misc{yao2026harness, title={Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows}, author={Yilun Yao and Xinyu Tan and Chao-Hsuan Liu and Yaoming Li and Zhengyang Wang and Wenhan Yu and Zhewen Tan and Yuxuan Tian and Guangxiang Zhao and Lin Sun and Xiangzheng Zhang and Tong Yang}, year={2026}, eprint={2605.27922}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2605.27922} }