Software Engineering on SWE tasks Diagnosis Search n = 30 (test)
53.68F1 ScoreParametricSkills
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ParametricSkillsBackbone=Qwen3-8B, Skill Type=Parametric (Hypernetwork generated)2026.06 | 53.68 | 89.32 | 61.67 | |
| In-ContextBackbone=Qwen3-8B, Skill Type=In-context skills2026.06 | 48.75 | 88.31 | 57.83 | |
| No-SkillBackbone=Qwen3-8B, Skill Type=None2026.06 | 47.61 | 88.37 | 60.33 | |
| SHINEBackbone=Qwen3-8B, Skill Type=Parametric (SHINE checkpoint)2026.06 | 37.2 | 87.58 | 48.17 |