Web Navigation / Skill Induction on Mind2Web Cross-Task GPT-4.1
63.2Success RatePolySkill
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PolySkillLibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 63.2 | 6 | 47 | |
| SKILLMIGRATORLibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 62.7 | 5.5 | 41 | |
| ASILibrary Regime=+Update, Base LLM=GPT-4.12026.06 | 59.4 | 6.4 | 66 | |
| PolySkillLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 55.4 | 6.3 | 43 | |
| SKILLMIGRATORLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 54.8 | 5.8 | 35 | |
| ReActLibrary Regime=Static, Base LLM=GPT-4.12026.06 | 53.8 | 7 | — | |
| ASILibrary Regime=Static, Base LLM=GPT-4.12026.06 | 52.3 | 6.6 | 50 |