GUI Agent Navigation on Mind2Web
45.68Success RateAUTOMMEMO
Evaluation Results
| Method | Links | |
|---|---|---|
| AUTOMMEMOBackbone=Qwen3.5-plus, Execution Model Category=Automatic Design2026.05 | 45.68 | |
| AUTOMMEMOExecution Model=Qwen3-VL-32B, Memory Schema Category=Automatic Design2026.05 | 45.25 | |
| M2Backbone=Qwen3.5-plus, Execution Model Category=Multimodal-based2026.05 | 39.25 | |
| ALMABackbone=Qwen3.5-plus, Execution Model Category=Automatic Design2026.05 | 36.3 | |
| G-MemoryBackbone=Qwen3.5-plus, Execution Model Category=Text-based2026.05 | 32.8 | |
| TrajectoryRetrievalBackbone=Qwen3.5-plus, Execution Model Category=Text-based2026.05 | 31.83 | |
| NoMemoryBackbone=Qwen3.5-plus, Execution Model Category=None2026.05 | 30.11 | |
| M2Execution Model=Qwen3-VL-32B, Memory Schema Category=Multimodal-based2026.05 | 29.63 | |
| ReasoningBankBackbone=Qwen3.5-plus, Execution Model Category=Text-based2026.05 | 26.25 | |
| XSkillBackbone=Qwen3.5-plus, Execution Model Category=Multimodal-based2026.05 | 25.08 | |
| ALMAExecution Model=Qwen3-VL-32B, Memory Schema Category=Automatic Design2026.05 | 24.29 | |
| NoMemoryExecution Model=Qwen3-VL-32B, Memory Schema Category=Baseline2026.05 | 22.31 | |
| XSkillExecution Model=Qwen3-VL-32B, Memory Schema Category=Multimodal-based2026.05 | 20.81 | |
| ReasoningBankExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 19.24 | |
| G-MemoryExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 19.2 | |
| AUTOMMEMOExecution Model=GPT-5.4-nano, Memory Schema Category=Automatic Design2026.05 | 18.65 | |
| ALMAExecution Model=GPT-5.4-nano, Memory Schema Category=Automatic Design2026.05 | 15.61 | |
| TrajectoryRetrievalExecution Model=Qwen3-VL-32B, Memory Schema Category=Text-based2026.05 | 15.4 | |
| G-MemoryExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 15.17 | |
| M2Execution Model=GPT-5.4-nano, Memory Schema Category=Multimodal-based2026.05 | 14.84 | |
| NoMemoryExecution Model=GPT-5.4-nano, Memory Schema Category=Baseline2026.05 | 12.63 | |
| ReasoningBankExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 9.77 | |
| TrajectoryRetrievalExecution Model=GPT-5.4-nano, Memory Schema Category=Text-based2026.05 | 9.76 | |
| XSkillExecution Model=GPT-5.4-nano, Memory Schema Category=Multimodal-based2026.05 | 6.95 |