Pinned Loading

1. OpenAgentEval/SWE-ABS OpenAgentEval/SWE-ABS Public

   [ICML 2026] SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark

   Python 17

2. CUHK-Shenzhen-SE/UTBoost CUHK-Shenzhen-SE/UTBoost Public

   [ACL'25] UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench

   Python 36

3. CUHK-Shenzhen-SE/RetromorphicTesting CUHK-Shenzhen-SE/RetromorphicTesting Public

   Jupyter Notebook 11

4. LightAD LightAD Public

   A toolkit for Light Log Anomaly Detection [ICSE'24]

   Python 22 5