SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Key points

• A new benchmark that evaluates repository exploration independently from patch generation.
• It derives trajectory-grounded, line-level ground truth from successful agent trajectories.
• It covers diverse coding settings with 848 issues, 10 languages, and 203 repositories.
• Agent exploration forms a clear top tier compared with classical retrieval.
• File-level hit rates are strong, but core line recall remains only 0.14 to 0.19, making it the bottleneck.
• Missing key context is more damaging to patch success than noisy context.

Paper links

External research summaries. These are not HDATF publications or measured product results.