Long-horizon robot task execution on Washing Task Suite
11.6Progress ScoreHuman + π sub mem
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Human + π sub memParadigm=Agentic2026.07 | 11.6 | 70 | |
| CortexParadigm=Agentic2026.07 | 10.5 | 55 | |
| πmemParadigm=End-to-end2026.07 | 6.5 | 0 | |
| π0.5Paradigm=End-to-end2026.07 | 3.7 | 0 |