Multi-Property Molecular Optimization (DRD2+SA) on ZINC 250k
69.5SRMolMem
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MolMemBackbone=Qwen2.5-1.5B, Optimization Paradigm=Expert2026.04 | 69.5 | 48 | 7.11 | |
| Reinvent 4Backbone=Transformer, Optimization Paradigm=Novice2026.04 | 37.5 | 50 | 5.54 | |
| PEIT-LLMBackbone=Llama3.1-8B, Optimization Paradigm=Apprentice, Optimization Strategy=Task-Specific LLM2026.04 | 34.5 | 46 | 5.61 | |
| Direct RetrievalBackbone=N/A, Optimization Paradigm=Apprentice, Optimization Strategy=Retrieval-based2026.04 | 23.5 | 43 | 2.64 | |
| ChemLLMBackbone=ChemLLM-7B, Optimization Paradigm=Apprentice, Optimization Strategy=Task-Specific LLM2026.04 | 22 | 55 | 5.4 | |
| LlaSMolBackbone=Mistral-7B, Optimization Paradigm=Apprentice, Optimization Strategy=Task-Specific LLM2026.04 | 16 | 47 | 3.79 | |
| GeLLM3OBackbone=Llama3.1-8B, Optimization Paradigm=Apprentice, Optimization Strategy=Task-Specific LLM2026.04 | 9 | 59 | 2.76 | |
| SFT-onlyBackbone=Qwen2.5-3B, Optimization Paradigm=Apprentice, Optimization Strategy=Prompting & SFT2026.04 | 7 | 61 | 2.41 | |
| SFT-onlyBackbone=Qwen2.5-1.5B, Optimization Paradigm=Apprentice, Optimization Strategy=Prompting & SFT2026.04 | 6.5 | 62 | 2.74 | |
| Direct PromptBackbone=Qwen2.5-1.5B, Optimization Paradigm=Apprentice, Optimization Strategy=Prompting & SFT2026.04 | 6 | 59 | 3.59 | |
| Direct PromptBackbone=Qwen2.5-3B, Optimization Paradigm=Apprentice, Optimization Strategy=Prompting & SFT2026.04 | 5 | 58 | 3.36 | |
| QMOBackbone=GRU, Optimization Paradigm=Novice2026.04 | 1 | 50 | 2.49 | |
| Graph-GABackbone=N/A, Optimization Paradigm=Novice2026.04 | 0 | 53 | 4.15 |