# LY-GWM-RoboCasa-Human300: Prediction-Guided Action Selection with a Graph Dynamics Model

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/k580bynb1dc5g7ug8fij9qpoc
- Original: https://arxiv.org/abs/2610.23274

## Summary

LY-GWM-RoboCasa-Human300 combines a Human300-fine-tuned GR00T-N1.5 action generator, an action-conditioned graph dynamics model, and a binary state-reward scorer; at inference it samples 4 action chunks and executes the candidate with the highest predicted-state reward.