Skip to content
AI News HubLIVE
Original source2 min read

CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions

Summary

This paper introduces CAFE, a framework that enables scene-driven robot autonomy by formulating and executing tasks from observations under predefined categories (cleaning, safety, storage/organization) without instance-specific goals or action sequences. CAFE maintains online memory of objects, functional zones, and execution states, and uses a rule-guided Trigger-LLM with Draft, Complete, and Audit LLMs to propose goals, resolve details, and check dependencies. Outcomes update memory for correction and discovery. Evaluated in 12 AI2-THOR scenes, Tri-LLM achieves higher GCR scores than baselines across three backbones and task-complexity tiers. Controls validate components, and LimoCobot traces illustrate storage, cleanup, and recovery from a failed grasp.

SourcearXiv RoboticsAuthor: Mingjia Chen, Xuewen Zhao, Philip Dames, Qi Mao, Fei Xie, Jun Chen
CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions
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 8 Nov 2026]

Title:CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions

View a PDF of the paper titled CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions, by Mingjia Chen and 5 other authors

View PDF HTML (experimental)

Abstract:Scene-driven robot autonomy requires selecting tasks from observations as well as executing them. We study scene-driven task formulation and execution under predefined cleaning, safety, and storage/organization categories, without instance-specific goals or action sequences. CAFE maintains online memory of objects, functional zones, and execution states. A rule-guided Trigger-LLM admits formulation from accumulated evidence; Draft, Complete, and Audit propose goals, resolve execution details, and check dependencies. Outcomes update memory for correction and subsequent discovery. Evaluation in 12 AI2-THOR scenes compares three backbones and task-complexity tiers using coverage, constraint, and execution metrics. Tri-LLM records higher GCR scores than the evaluated baselines across three backbones and task-complexity tiers. Controls examine completion, auditing, zones, feedback, triggering, and prompt examples. LimoCobot traces illustrate storage, cleanup, and recovery from a failed grasp. The study examines how shared scene state connects task discovery to execution and outcome-driven revision.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.12983 [cs.RO]

(or arXiv:2611.12983v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.12983

arXiv-issued DOI via DataCite

Submission history

From: Mingjia Chen [view email] [v1] Sun, 8 Nov 2026 08:08:15 UTC (46,673 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions, by Mingjia Chen and 5 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

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

EngineersIntermediate

Key points

  • CAFE autonomously formulates and executes tasks from scene observations without instance-specific instructions, using predefined categories.
  • The framework combines online memory, a rule-guided Trigger-LLM, and Draft-Complete-Audit LLM modules for closed-loop operation.
  • Tri-LLM outperforms baselines in GCR scores across three backbones and complexity tiers in AI2-THOR, with controls confirming module contributions.
  • LimoCobot traces demonstrate storage, cleanup, and recovery from grasp failures.

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