Agent Continuous Improvement on CoSQL StreamBench (32 held-out episodes)
73.5Pass@4Memory w/ MEMOPILOT
Evaluation Results
| Method | Links | |
|---|---|---|
| Memory w/ MEMOPILOTMemory Strategy=MEMOPILOT, Execution Agent=Qwen2.5-14B-Instruct2026.06 | 73.5 | |
| Full HistoryMemory Strategy=Full History, Execution Agent=Qwen2.5-14B-Instruct2026.06 | 70 | |
| No MemoryMemory Strategy=No Memory, Execution Agent=Qwen2.5-14B-Instruct2026.06 | 69.5 | |
| Memory w/ DeepSeek-V3.2Memory Strategy=DeepSeek-V3.2, Execution Agent=Qwen2.5-14B-Instruct2026.06 | 67.5 | |
| Memory w/ Qwen2.5-14BMemory Strategy=Qwen2.5-14B, Execution Agent=Qwen2.5-14B-Instruct2026.06 | 66 |