SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Feat: sb-cli support for verified
Kilian Lieretca3cfb365a36
diff --git a/sweagent/run/hooks/swe_bench_evaluate.py b/sweagent/run/hooks/swe_bench_evaluate.pyindex f3ed8a6b..67bdae27 100644--- a/sweagent/run/hooks/swe_bench_evaluate.py+++ b/sweagent/run/hooks/swe_bench_evaluate.py@@ -17,7 +17,7 @@ from sweagent.utils.log import get_loggerclass SweBenchEvaluate(RunHook):- _SUBSET_MAP = {"lite": "swe-bench_lite"}+ _SUBSET_MAP = {"lite": "swe-bench_lite", "verified": "swe-bench_verified"}def __init__(self, output_dir: Path, subset: str, split: str, continuous_submission_every: int = 0) -> None:super().__init__()