Database task execution on Lifelong-DB (held-out)
94.2Success Rate (SR)MemRL
Evaluation Results
| Method | Links | |
|---|---|---|
| MemRLType=Q-value episodic memory, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 94.2 | |
| Mem0Type=Entity-centric memory, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 93.5 | |
| MemPType=Procedural distillation, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 92.8 | |
| RAGType=Semantic retrieval, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 92 | |
| Self-RAGType=Critique-filtered retrieval, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 88.1 | |
| No MemoryType=Single-shot LLM, Base Model=GPT-4o-mini, Memory=Frozen2026.03 | 84.1 |