Towards Agentic Robots: Model, Data, Environment, and Harness

Hugging Face Daily Papers Papers
robotics foundation-models vision-language-action survey agentic-systems world-models

Summary

该论文提供了关于「智能体机器人」（agentic robots）的统一综述，将现有研究组织为模型、数据、环境和评测（Harness）四大功能领域的17个类别，并探讨了从机器人策略到智能体系统的演进及未来开放挑战。

Foundation models are driving a paradigm shift in robotic intelligence, moving beyond low-level action prediction to goal-directed orchestration of data collection, model training, task planning, and real-world execution. We characterize this emerging paradigm as an agentic robots, in which agents reason over human instructions, interact with robotic environments, rectify execution errors autonomously, and dynamically adjust operational strategies. Although this field develops fast, current studies are not well connected. Researchers have no consistent view of how to combine different agentic functions into a complete robot system. This paper provides a unified overview of existing research on agentic robots. We first trace the development from robot policies to agentic systems, covering vision-language-action models, world models, and world-action models. We then clarify the definition and scope of agentic robots and organize existing research into seventeen categories across four functional domains: Model, Data, Environment, and Harness. Across these domains, we examine how agents shape model learning and robot decisions, collect and curate robot data, construct worlds, tasks, and tests for learning and evaluation, and organize capabilities for robot use. Finally, we discuss open challenges and outline directions for future research. Looking forward, we hope this work contributes to a clearer understanding of agentic robots and supports new approaches to making them more capable, reliable, and adaptive.
Original Article
View Cached Full Text

Cached at: 10/15/26, 07:04 AM

Paper page - Towards Agentic Robots: Model, Data, Environment, and Harness

Source: https://huggingface.co/papers/2610.20442 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Foundationmodelsaredrivingaparadigmshiftinroboticintelligence,movingbeyondlow-levelactionpredictiontogoal-directedorchestrationofdatacollection,modeltraining,taskplanning,andreal-worldexecution.Wecharacterizethisemergingparadigmasanagenticrobots,inwhichagentsreasonoverhumaninstructions,interactwithroboticenvironments,rectifyexecutionerrorsautonomously,anddynamicallyadjustoperationalstrategies.Althoughthisfielddevelopsfast,currentstudiesarenotwellconnected.Researchershavenoconsistentviewofhowtocombinedifferentagenticfunctionsintoacompleterobotsystem.Thispaperprovidesaunifiedoverviewofexistingresearchonagenticrobots.Wefirsttracethedevelopmentfromrobotpoliciestoagenticsystems,coveringvision-language-actionmodels,worldmodels,andworld-actionmodels.Wethenclarifythedefinitionandscopeofagenticrobotsandorganizeexistingresearchintoseventeencategoriesacrossfourfunctionaldomains:Model,Data,Environment,andHarness.Acrossthesedomains,weexaminehowagentsshapemodellearningandrobotdecisions,collectandcuraterobotdata,constructworlds,tasks,andtestsforlearningandevaluation,andorganizecapabilitiesforrobotuse.Finally,wediscussopenchallengesandoutlinedirectionsforfutureresearch.Lookingforward,wehopethisworkcontributestoaclearerunderstandingofagenticrobotsandsupportsnewapproachestomakingthemmorecapable,reliable,andadaptive.

View arXiv pageView PDFGitHub25Add to collection

Get this paper in your agent:

hf papers read 2610\.20442

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.20442 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.20442 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.20442 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Democratizing Robot-Use Agents: A Unified Harness with Open Models

Hugging Face Daily Papers

The paper introduces uni-robot-agent, a unified harness enabling open-weight robot-use agents to outperform proprietary models like GPT-6 Astra-RoboProbe on zero-shot manipulation benchmarks, and identifies four core capabilities that future robot-use agent training should jointly develop.

Work Agents: Systems, Capabilities, and Optimization

Papers with Code Trending

该论文提出了一个统一的“工作智能体”（work agents）框架，将基础模型与运行时框架结合以可靠执行复杂数字任务，引入持久性与开放性两个维度，并系统分析能力族、模型与框架优化及评估方法。