# PAL: A Hierarchical Memory Framework with Plan-First, Act-Later Streaming Reasoning for Robot Manipulation

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/fnr25z1j7r31p17x0red4euns
- Original: https://arxiv.org/abs/2610.29329

## Summary

The paper proposes PAL (Plan first, Act Later), a hierarchical memory framework for vision-language robot manipulation. A high-level vision-language model (VLM) converts streaming visual observations into a subtask_list, and at execution time selects the currently relevant subtask from it to pass to a low-level vision-language-action (VLA) policy.