Software Engineering Issue Resolution on SWE-Bench Live Lite
0.224Resolve RateHybrid
Evaluation Results
| Method | Links | |
|---|---|---|
| HybridFeedback=Hybrid (Execution-free + Execution-based)2025.12 | 0.224 | |
| Execution-free onlyFeedback=Execution-free (SWE-RM)2025.12 | 0.204 | |
| Execution-based onlyFeedback=Execution-based2025.12 | 0.2 | |
| Poor Calibrated RMFeedback=Ablated RM (Poorly Calibrated)2025.12 | 0.12 |