Adversarial Robustness in Web Environments on WASP
93.8GitLab Success Rate (SR)SkillWeaver
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| SkillWeaverSkill Learning Setting=Self Proposal2026.06 | 93.8 | 12.5 | 55.6 | 5.6 | 77.4 | 9.5 | |
| SKILLHARNESSSkill Learning Setting=Self Proposal2026.06 | 93.8 | 0 | 61.1 | 2.8 | 79.8 | 1.2 | |
| SKILLHARNESS w/o updateSkill Learning Setting=Task Training2026.06 | 91.7 | 0 | 68.8 | 6.2 | 82.5 | 2.5 | |
| SKILLHARNESSSkill Learning Setting=Task Training2026.06 | 91.7 | 0 | 75 | 6.2 | 85 | 2.5 | |
| DefaultSkill Learning Setting=Self Proposal2026.06 | 64.6 | 10.4 | 47.2 | 25 | 57.1 | 16.7 | |
| DefaultSkill Learning Setting=Task Training2026.06 | 62.5 | 16.7 | 47.2 | 25 | 56.4 | 20 | |
| ASI w/o updateSkill Learning Setting=Task Training2026.06 | 50 | 83.3 | 56.3 | 68.7 | 52.5 | 77.5 | |
| ASISkill Learning Setting=Task Training2026.06 | 50 | 79.2 | 50 | 50 | 50 | 67.5 |