List your company

E-commerce Navigation and Search on WebShop (semantic shift Hidden drift)

100ScoreNo Memory (Plain)
11.634.5557.580.45Jan 27, 2026

Evaluation results

MethodLinks
No Memory (Plain)Backbone=Qwen3-30B, Agent Architecture=No Memory, GLOVE Augmentation=false2026.01100
VanillaBackbone=Qwen3-30B, Agent Architecture=Vanilla, GLOVE Augmentation=false2026.01100
Vanilla + GLOVEBackbone=Qwen3-30B, Agent Architecture=Vanilla, GLOVE Augmentation=true2026.01100
MemoryBankBackbone=Qwen3-30B, Agent Architecture=MemoryBank, GLOVE Augmentation=false2026.01100
MemoryBank + GLOVEBackbone=Qwen3-30B, Agent Architecture=MemoryBank, GLOVE Augmentation=true2026.01100
VoyagerBackbone=Qwen3-30B, Agent Architecture=Voyager, GLOVE Augmentation=false2026.01100
Voyager + GLOVEBackbone=Qwen3-30B, Agent Architecture=Voyager, GLOVE Augmentation=true2026.01100
Generative AgentBackbone=Qwen3-30B, Agent Architecture=Generative Agent, GLOVE Augmentation=false2026.01100
Generative Agent + GLOVEBackbone=Qwen3-30B, Agent Architecture=Generative Agent, GLOVE Augmentation=true2026.01100
MemoryBank + GLOVELLM Backbone=GPT-4o, Base Agent=MemoryBank2026.0198.8
Voyager + GLOVELLM Backbone=GPT-4o, Base Agent=Voyager2026.0198.8
Vanilla +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0198.8
MemoryBank +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0198.8
Voyager +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0198.8
Vanilla + GLOVEBackbone=DeepSeek-V3.22026.0197.5
MemoryBank + GLOVEBackbone=DeepSeek-V3.22026.0197.5
Voyager + GLOVEBackbone=DeepSeek-V3.22026.0197.5
Generative Agent + GLOVEBackbone=DeepSeek-V3.22026.0197.5
Generative Agent +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0197.5
No Memory (Plain)LLM=Grok-32026.0196.2
Voyager + GLOVEBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0195
No Memory (Plain)Backbone=DeepSeek-V3.22026.0195
Vanilla + GLOVELLM Backbone=GPT-4o, Base Agent=Vanilla2026.0193.8
MemoryBank + GLOVEBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0188.8
No Memory (Plain)LLM Backbone=GPT-4o2026.0187.5
MemoryBankBackbone=DeepSeek-V3.22026.0182.5
Generative AgentLLM=Grok-32026.0182.5
MemoryBankBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0181.2
MemoryBankLLM Backbone=GPT-4o2026.0181.2
MemoryBankLLM=Grok-32026.0181.2
No Memory (Plain)Backbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0180
Vanilla + GLOVEBackbone=Llama3.1-8B2026.0176.2
VanillaBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0175
Vanilla + GLOVEBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0175
VoyagerBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0175
Generative AgentBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0175
Generative Agent + GLOVEBackbone=Llama3.3-70B, Drift Type=Implicit, Stage=Hidden drift2026.0175
VanillaBackbone=Qwen2.5-7B2026.0175
Vanilla + GLOVEBackbone=Qwen2.5-7B2026.0175
MemoryBank + GLOVEBackbone=Qwen2.5-7B2026.0175
VoyagerBackbone=Qwen2.5-7B2026.0175
Voyager + GLOVEBackbone=Qwen2.5-7B2026.0175
Generative AgentBackbone=Qwen2.5-7B2026.0175
Generative Agent + GLOVEBackbone=Qwen2.5-7B2026.0175
VanillaBackbone=DeepSeek-V3.22026.0175
VoyagerBackbone=DeepSeek-V3.22026.0175
Generative AgentBackbone=DeepSeek-V3.22026.0175
VanillaLLM Backbone=GPT-4o2026.0175
VoyagerLLM Backbone=GPT-4o2026.0175
Generative AgentLLM Backbone=GPT-4o2026.0175
Generative Agent + GLOVELLM Backbone=GPT-4o, Base Agent=Generative Agent2026.0175
VanillaLLM=Grok-32026.0175
VoyagerLLM=Grok-32026.0175
MemoryBank + GLOVEBackbone=Llama3.1-8B2026.0167.5
No Memory (Plain)Backbone=Llama3.1-8B2026.0160
Generative Agent + GLOVEBackbone=Llama3.1-8B2026.0160
Generative AgentBackbone=Llama3.1-8B2026.0155
MemoryBankBackbone=Qwen2.5-7B2026.0153.8
Voyager + GLOVEBackbone=Llama3.1-8B2026.0142.5
VanillaBackbone=Llama3.1-8B2026.0136.2
MemoryBankBackbone=Llama3.1-8B2026.0127.5
VoyagerBackbone=Llama3.1-8B2026.0126.2
No Memory (Plain)Backbone=Qwen2.5-7B2026.0115