Question Answering on RULER-HQA 896K
76.56Normalized sub-EM AccuracyRL-MemAgent-7B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RL-MemAgent-7BModel=RL-MemAgent-7B2026.02 | 76.56 | — | |
| LycheeMemory-7B w/o GateModel=LycheeMemory-7B, Gate=disabled2026.02 | 75.78 | — | |
| LycheeMemory-7BModel=LycheeMemory-7B, Gate=enabled2026.02 | 72.66 | 17.7 | |
| Search-R1Model=Search-R12026.02 | 67.71 | — | |
| RAG + Qwen2.5-7B-InstructModel=RAG + Qwen2.5-7B-Instruct2026.02 | 61.72 | — | |
| QwenLong-L1-32BModel=QwenLong-L1-32B2026.02 | 11.72 | — | |
| DS-Distill-Qwen-32BModel=DS-Distill-Qwen-32B2026.02 | 7.03 | — | |
| DS-Distill-Qwen-14BModel=DS-Distill-Qwen-14B2026.02 | 6.25 | — | |
| Qwen2.5-Instruct-14B-1MModel=Qwen2.5-Instruct-14B-1M2026.02 | 0 | — | |
| Qwen2.5-Instruct-7B-1MModel=Qwen2.5-Instruct-7B-1M2026.02 | 0 | — | |
| DS-Distill-Qwen-7BModel=DS-Distill-Qwen-7B2026.02 | 0 | — |