Skip to content
AI News HubLIVE
Original source2 min read

GEMS: Generation and Experience Memory for Subgoal-Guided Long-Horizon World Model Planning

Summary

GEMS combines temporally structured generated subgoals with a Latent Experience Memory (LEM) to guide long-horizon planning with a frozen world model. A distance gate decides whether predicted outcomes are compared against the generated subgoal or a selected memory state. It achieves 92.8% on Cube, 68.4% on Push-T, and 54.1% on Meta-World, outperforming the strongest baseline by 24.0, 7.3, and 22.2 percentage points respectively.

SourcearXiv RoboticsAuthor: Yangchen Zhao, Ali Payani, Caiwen Ding
GEMS: Generation and Experience Memory for Subgoal-Guided Long-Horizon World Model Planning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:GEMS: Generation and Experience Memory for Subgoal-Guided Long-Horizon World Model Planning

View a PDF of the paper titled GEMS: Generation and Experience Memory for Subgoal-Guided Long-Horizon World Model Planning, by Yangchen Zhao and 2 other authors

View PDF HTML (experimental)

Abstract:Visual world models enable effective short-horizon goal-conditioned planning, such as reaching nearby targets and pushing objects over short distances, by predicting candidate action outcomes and comparing their representations with a goal representation. However, extending this approach to long-horizon tasks is challenging: prediction errors accumulate over extended rollouts, while latent-space similarity to distant goals provides limited guidance for ranking candidate outcomes. Existing methods address these limitations by introducing intermediate subgoals, either generated by learned models or selected from experience memory. Generated subgoals can contain hallucinations or be inaccurate in aspects such as object positions and timing. Memory-based approaches are constrained by experience coverage and may lack precise guidance for selecting appropriate intermediate states from stored observations. We introduce GEMS, which generates temporally structured subgoals to guide action search and state selection from Latent Experience Memory (LEM). A distance gate determines whether predicted outcomes are evaluated against the generated subgoal or the selected memory state. Experiments across six tasks and task suites spanning manipulation, navigation, and reaching demonstrate the effectiveness of GEMS for long-horizon planning. GEMS outperforms state-of-the-art world-model planning baselines across different manipulation settings, achieving success rates of 92.8% on Cube, 68.4% on Push-T, and 54.1% on Meta-World. It improves over the strongest evaluated baseline on these tasks by 24.0, 7.3, and 22.2 percentage points, respectively. These results demonstrate that generated subgoals and experience memory can jointly strengthen long-horizon planning with a frozen world model.

Subjects:

Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.25134 [cs.RO]

(or arXiv:2611.25134v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.25134

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yangchen Zhao [view email] [v1] Wed, 18 Nov 2026 20:13:01 UTC (2,405 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GEMS: Generation and Experience Memory for Subgoal-Guided Long-Horizon World Model Planning, by Yangchen Zhao and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs cs.CV

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • GEMS jointly uses generated subgoals and latent experience memory to overcome prediction error accumulation and weak distant-goal guidance in long-horizon planning.
  • A distance gate dynamically selects whether candidate outcomes are evaluated against a generated subgoal or a memory state.
  • Across six tasks, GEMS improves success rates by up to 24.0 percentage points over state-of-the-art world-model planning baselines.

Highlights and analysis are generated automatically and may contain errors. Check the original source.