SOURCE-LINKED INTELLIGENCE

2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Long-horizon robot manipulation requires memory, but not necessarily inside the action policy. To address such tasks, current agentic systems often combine VLAs with planners and geometric tools, sometimes using additional depth or calibrated geometry. These systems confound attribution: gains may come from richer observations or alternative motor tools, while failures may stem from either the policy or an under-specified language interface. We isolate this question through a deliberately constrained design: less tool breadth, but greater interface bandwidth. 2AM makes a multimodal Agent the s

Read original source ↗ Open in workspace

recordType

paper

region

Global