Paper Detail

When the Past Shapes Action: Understanding Embodied Memory

Siqi Li, Ziyi Bai, Xinrun Xu, Tinglei Huang, Börje F. Karlsson

arxiv Score 19.3

Published 2026-10-30 · First seen 2026-11-02

General AI

Abstract

Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{li2026when,
  title = {When the Past Shapes Action: Understanding Embodied Memory},
  author = {Siqi Li and Ziyi Bai and Xinrun Xu and Tinglei Huang and Börje F. Karlsson},
  year = {2026},
  abstract = {Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving d},
  url = {https://arxiv.org/abs/2610.41688},
  keywords = {cs.RO, cs.AI, cs.LG},
  eprint = {2610.41688},
  archiveprefix = {arXiv},
}

Metadata

{}