List your company

Grid World Navigation on FrozenLake (Source)

67.5ScoreMemoryBank + GLOVE
-2.715.52533.7551.975Jan 27, 2026

Evaluation results

MethodLinks
MemoryBank + GLOVELLM Backbone=GPT-4o, Base Agent=MemoryBank2026.0167.5
VoyagerLLM Backbone=GPT-4o2026.0167.5
MemoryBankLLM Backbone=GPT-4o2026.0162.5
Generative AgentLLM Backbone=GPT-4o2026.0162.5
Generative Agent + GLOVELLM Backbone=GPT-4o, Base Agent=Generative Agent2026.0162.5
VoyagerLLM=Grok-32026.0162.5
Generative Agent +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0157.5
VanillaBackbone=DeepSeek-V3.22026.0152.5
Vanilla + GLOVEBackbone=DeepSeek-V3.22026.0150
VanillaLLM Backbone=GPT-4o2026.0147.5
Voyager + GLOVELLM Backbone=GPT-4o, Base Agent=Voyager2026.0140
Vanilla + GLOVELLM Backbone=GPT-4o, Base Agent=Vanilla2026.0135
Generative AgentLLM=Grok-32026.0135
Voyager + GLOVEBackbone=DeepSeek-V3.22026.0130
VanillaLLM=Grok-32026.0130
Vanilla +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0130
Voyager +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0127.5
VoyagerBackbone=DeepSeek-V3.22026.0122.5
Generative AgentBackbone=DeepSeek-V3.22026.0122.5
Generative Agent + GLOVEBackbone=DeepSeek-V3.22026.0120
MemoryBank +GLOVELLM=Grok-3, Augmentation=GLOVE2026.0120
VoyagerBackbone=Llama3.1-8B2026.0120
Generative Agent + GLOVEBackbone=Llama3.1-8B2026.0117.5
MemoryBankLLM=Grok-32026.0115
Voyager + GLOVEBackbone=Llama3.1-8B2026.0115
Generative AgentBackbone=Llama3.1-8B2026.0115
Vanilla + GLOVEBackbone=Llama3.1-8B2026.0112.5
MemoryBankBackbone=DeepSeek-V3.22026.0110
MemoryBank + GLOVEBackbone=DeepSeek-V3.22026.0110
VanillaBackbone=Llama3.1-8B2026.0110
MemoryBankBackbone=Llama3.1-8B2026.017.5
MemoryBank + GLOVEBackbone=Llama3.1-8B2026.015
No Memory (Plain)Backbone=DeepSeek-V3.22026.010
No Memory (Plain)LLM Backbone=GPT-4o2026.010
No Memory (Plain)LLM=Grok-32026.010
No Memory (Plain)Backbone=Llama3.1-8B2026.010