Language-based decision-making on WebShop (test)
81.4RewardAUTOGUIDE + Reflexion
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AUTOGUIDE + ReflexionOffline data=true, Context aware=true, Base agent model=GPT-3.5-turbo, Reflexion=true, Reflexion model=GPT-4-turbo2024.03 | 81.4 | 57 | |
| ReAct + ReflexionOffline data=false, Context aware=false, Base agent model=GPT-3.5-turbo, Reflexion=true, Reflexion model=GPT-4-turbo2024.03 | 77.1 | 51 | |
| AUTOGUIDEOffline data=true, Context aware=true, Base agent model=GPT-3.5-turbo, Reflexion=false2024.03 | 73.4 | 46 | |
| ExpeL + ReflexionOffline data=true, Context aware=false, Base agent model=GPT-3.5-turbo, Reflexion=true, Reflexion model=GPT-4-turbo2024.03 | 71.7 | 42 | |
| ReActOffline data=false, Context aware=false, Base agent model=GPT-3.5-turbo, Reflexion=false2024.03 | 66.4 | 30 | |
| ExpeLOffline data=true, Context aware=false, Base agent model=GPT-3.5-turbo, Reflexion=false2024.03 | 60.9 | 35 |