arXivShaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, Xiaodong GuFri, Jun 5, 2026, 7:08 AM PDT
score 15.4
New benchmark measures how coding agents explore repositories
Original: SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Source: arxiv.org ↗
Writing ELI5 summary…