Continuous Control on MountainCar Explicit Structural Drift II
100Success Rate (Source)Qwen3-30B
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen3-30BBackbone=Qwen3-30B, GLOVE Augmentation=false2026.01 | 100 | 100 | — | — | |
| Qwen3-30B + GLOVEBackbone=Qwen3-30B, GLOVE Augmentation=true2026.01 | 100 | 100 | — | — | |
| GPT-4o + GLOVEBackbone=GPT-4o, GLOVE Augmentation=true2026.01 | 100 | 100 | 10 | — | |
| Grok-3Backbone=Grok-3, GLOVE Augmentation=false2026.01 | 100 | 100 | — | — | |
| Grok-3 + GLOVEBackbone=Grok-3, GLOVE Augmentation=true2026.01 | 100 | 100 | — | — | |
| GPT-4oBackbone=GPT-4o, GLOVE Augmentation=false2026.01 | 96.2 | 90 | — | — | |
| Llama3.1-8BBackbone=Llama3.1-8B, GLOVE Augmentation=false2026.01 | 93.8 | 65 | — | — | |
| Llama3.1-8B + GLOVEBackbone=Llama3.1-8B, GLOVE Augmentation=true2026.01 | 93.8 | 68.8 | 3.8 | — | |
| Llama3.3-70BBackbone=Llama3.3-70B, GLOVE Augmentation=false2026.01 | 0 | 0 | — | — | |
| Llama3.3-70B + GLOVEBackbone=Llama3.3-70B, GLOVE Augmentation=true2026.01 | 0 | 0 | 0 | — | |
| Qwen2.5-7BBackbone=Qwen2.5-7B, GLOVE Augmentation=false2026.01 | 0 | 0 | — | — | |
| Qwen2.5-7B + GLOVEBackbone=Qwen2.5-7B, GLOVE Augmentation=true2026.01 | 0 | 0 | 0 | — | |
| DeepSeek-V3.2Backbone=DeepSeek-V3.2, GLOVE Augmentation=false2026.01 | 0 | 0 | — | — | |
| DeepSeek-V3.2 + GLOVEBackbone=DeepSeek-V3.2, GLOVE Augmentation=true2026.01 | 0 | 0 | 0 | — | |
| Generative AgentBackbone=GPT-4o, Agent Architecture=Generative Agent, GLOVE Augmentation=false2026.01 | — | — | — | 70 | |
| GLOVEBackbone=GPT-4o, Agent Architecture=Vanilla, GLOVE Augmentation=true2026.01 | — | — | — | 100 | |
| GLOVEBackbone=GPT-4o, Agent Architecture=MemoryBank, GLOVE Augmentation=true2026.01 | — | — | — | 100 | |
| GLOVEBackbone=GPT-4o, Agent Architecture=Voyager, GLOVE Augmentation=true2026.01 | — | — | — | 100 | |
| GLOVEBackbone=GPT-4o, Agent Architecture=Generative Agent, GLOVE Augmentation=true2026.01 | — | — | — | 100 | |
| MemoryBankBackbone=GPT-4o, Agent Architecture=MemoryBank, GLOVE Augmentation=false2026.01 | — | — | — | 100 | |
| No Memory (Plain)Backbone=GPT-4o, Agent Architecture=Plain, GLOVE Augmentation=false2026.01 | — | — | — | 55 | |
| VanillaBackbone=GPT-4o, Agent Architecture=Vanilla, GLOVE Augmentation=false2026.01 | — | — | — | 90 | |
| VoyagerBackbone=GPT-4o, Agent Architecture=Voyager, GLOVE Augmentation=false2026.01 | — | — | — | 100 |