PAL: Streaming Reasoning for Executable Memory in Robot Control
Overview
This research proposes PAL, a hierarchical memory framework for vision-language robot manipulation. It maintains a short-term visual buffer, semantic-event memory, and an executable subtask list. A high-level vision-language model converts streaming observations into subtasks, which are then executed by a low-level policy. PAL achieves 56.05% success on RoboMME and 60.83% in real-world tasks, outperforming existing baselines.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Artifact availability · code: reported pending
“hierarchical memory improves long-horizon visual reasoning and robot control. Code and videos can be found on our website: https://qinghangliu.github.io/pal-webpage/”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T21:35:52.620Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T21:35:30.293Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPlan First, Act Later: Streaming Reasoning for Executable Memory in Robot Control
This research proposes PAL, a hierarchical memory framework for vision-language robot manipulation. It maintains a short-term visual buffer, semantic-event memory, and an executable subtask list. A high-level vision-language model converts streaming observations into subtasks, which are then executed by a low-level policy. PAL achieves 56.05% success on RoboMME and 60.83% in real-world tasks, outperforming existing baselines.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).