| Paper | Code | Success Rate | ModelName | ReleaseDate |
|---|---|---|---|---|
| Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence | ✓ Link | 93.56 | Zetta + frozen GR00T N1.5 | 2026-08-17 |
| Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence | ✓ Link | 81.0 | HexaModel v0.1 (extra data) | 2026-09-28 |
| ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training | ✓ Link | 78.1 | ZimaBlue (Slow System) | 2026-08-31 |
| OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining | ✓ Link | 69.7 | OpenWAM-alpha | 2026-09-07 |
| Can World and Action Modeling Benefit Each Other under Unified Causal Training? | ✓ Link | 68.78 | OneWM | 2026-10-15 |
| RLDX-1 Technical Report | ✓ Link | 67.3 | RLDX-1 | 2026-05-05 |