# Tsinghua and National University of Singapore Propose ParallelWorld: Multi-Step Rehearsal Improves Embodied Planning Success Rate

- Source: 机器之心 · 微信公众号
- Published: 2026-10-26T06:13:46.000Z
- RoboHot: https://robohot.news/en/items/ah8xqhf13f1napdeoa15vcf6t
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651070119&idx=3&sn=0b5bcfa3dbbba88884cf9dbff0a0c6a9&chksm=8563c684392a7dff6e0e5f989df391fa8971f1f3c907273b95de207b34961d882fa4d01c1194&scene=126&sessionid=1793022368#rd

## Summary

Researchers from Tsinghua University and the National University of Singapore propose ParallelWorld, which adds multi-step candidate future rehearsal to high-level planning for embodied agents, raising task success rate from 56% to 83%. The method generates and verifies multiple candidate action branches in a rehearsal loop; during execution it takes only the first action of the selected trajectory, then replans based on new observations. Success rates were higher than the direct baseline across eight LIBERO-Pro settings, but adaptive search took on average about 5.8 times as long as direct execution.