Web Navigation on WebShop Source
100Success RateMemoryBank
Evaluation Results
| Method | Links | |
|---|---|---|
| MemoryBankLLM Backbone=Llama3.3-70B2026.01 | 100 | |
| MemoryBank + GLOVELLM Backbone=Llama3.3-70B2026.01 | 100 | |
| MemoryBank + GLOVEBackbone=GPT-4o, Agent Architecture=MemoryBank, Augmentation=GLOVE2026.01 | 100 | |
| Vanilla + GLOVELLM Backbone=Llama3.3-70B2026.01 | 95 | |
| Generative AgentLLM Backbone=Llama3.3-70B2026.01 | 95 | |
| VanillaLLM Backbone=Llama3.3-70B2026.01 | 90 | |
| VoyagerLLM Backbone=Llama3.3-70B2026.01 | 90 | |
| Voyager + GLOVELLM Backbone=Llama3.3-70B2026.01 | 90 | |
| Generative Agent + GLOVELLM Backbone=Llama3.3-70B2026.01 | 90 | |
| Vanilla + GLOVEBase LLM=Grok-3, Agent Architecture=Vanilla, GLOVE Augmentation=true, Drift Visibility=Verifier-Visible2026.01 | 90 | |
| MemoryBankBase LLM=Grok-3, Agent Architecture=MemoryBank, GLOVE Augmentation=false, Drift Visibility=Verifier-Visible2026.01 | 90 | |
| VanillaBase LLM=Grok-3, Agent Architecture=Vanilla, GLOVE Augmentation=false, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| MemoryBank + GLOVEBase LLM=Grok-3, Agent Architecture=MemoryBank, GLOVE Augmentation=true, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| VoyagerBase LLM=Grok-3, Agent Architecture=Voyager, GLOVE Augmentation=false, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| Voyager + GLOVEBase LLM=Grok-3, Agent Architecture=Voyager, GLOVE Augmentation=true, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| Generative AgentBase LLM=Grok-3, Agent Architecture=Generative Agent, GLOVE Augmentation=false, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| Generative Agent + GLOVEBase LLM=Grok-3, Agent Architecture=Generative Agent, GLOVE Augmentation=true, Drift Visibility=Verifier-Visible2026.01 | 85 | |
| VanillaBackbone=GPT-4o, Agent Architecture=Vanilla, Augmentation=None2026.01 | 85 | |
| Vanilla + GLOVEBackbone=GPT-4o, Agent Architecture=Vanilla, Augmentation=GLOVE2026.01 | 85 | |
| MemoryBankBackbone=GPT-4o, Agent Architecture=MemoryBank, Augmentation=None2026.01 | 85 | |
| VoyagerBackbone=GPT-4o, Agent Architecture=Voyager, Augmentation=None2026.01 | 85 | |
| Voyager + GLOVEBackbone=GPT-4o, Agent Architecture=Voyager, Augmentation=GLOVE2026.01 | 80 | |
| Generative AgentBackbone=GPT-4o, Agent Architecture=Generative Agent, Augmentation=None2026.01 | 80 | |
| Generative Agent + GLOVEBackbone=GPT-4o, Agent Architecture=Generative Agent, Augmentation=GLOVE2026.01 | 75 | |
| No Memory (Plain)LLM Backbone=Llama3.3-70B2026.01 | 50 | |
| No Memory (Plain)Base LLM=Grok-3, Agent Architecture=No Memory, GLOVE Augmentation=false, Drift Visibility=Verifier-Visible2026.01 | 20 | |
| No Memory (Plain)Backbone=GPT-4o, Memory=None2026.01 | 15 |