Web Navigation and Skill Induction on Mind2Web Cross-Website GPT-4.1
61.3Success Rate (SR)PolySkill
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PolySkillLibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 61.3 | 6.5 | 53 | |
| SKILLMIGRATORLibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 60.5 | 5.9 | 47 | |
| ASILibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 58.7 | 6.9 | 71 | |
| PolySkillLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 57.6 | 6.8 | 44 | |
| SKILLMIGRATORLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 57.1 | 6.2 | 38 | |
| ReActLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 56.2 | 7.5 | — | |
| ASILibrary Regime=Static, Base LLM=GPT-4.12026.06 | 54.9 | 7.1 | 47 |