GUI Agent on WebVoyager
51.84Success RateAUTOMMEMO
Evaluation Results
| Method | Links | |
|---|---|---|
| AUTOMMEMOExecution Model=Qwen3-VL-32B, Memory Schema Category=Automatic Design2026.05 | 51.84 | |
| ALMAExecution Model=Qwen3-VL-32B, Memory Schema Category=Automatic Design2026.05 | 45.73 | |
| ReasoningBankExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 45.36 | |
| TrajectoryRetrievalExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 43.9 | |
| M2Execution Model=Qwen3-VL-32B, Memory Schema Category=Multimodal-based2026.05 | 43.59 | |
| AUTOMMEMOExecution Model=GPT-5.4-nano, Memory Schema Category=Automatic Design2026.05 | 42.3 | |
| XSkillExecution Model=Qwen3-VL-32B, Memory Schema Category=Multimodal-based2026.05 | 41.04 | |
| M2Execution Model=GPT-5.4-nano, Memory Schema Category=Multimodal-based2026.05 | 38.33 | |
| NoMemoryExecution Model=GPT-5.4-nano, Memory Schema Category=Baseline2026.05 | 37.89 | |
| ALMAExecution Model=GPT-5.4-nano, Memory Schema Category=Automatic Design2026.05 | 37.47 | |
| G-MemoryExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 37.35 | |
| G-MemoryExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 36.5 | |
| NoMemoryExecution Model=Qwen3-VL-32B, Memory Schema Category=Baseline2026.05 | 36.32 | |
| ReasoningBankExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 35.51 | |
| TrajectoryRetrievalExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 34.82 | |
| XSkillExecution Model=GPT-5.4-nano, Memory Schema Category=Multimodal-based2026.05 | 24.89 |