Guardado en:
Detalles Bibliográficos
Autores principales: Zhou, Xueyang, Sun, Yihan, Gong, Xijie, Tie, Guiyao, Zhou, Pan, Sun, Lichao, Chen, Yongchao
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.13800
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917410601172992
author Zhou, Xueyang
Sun, Yihan
Gong, Xijie
Tie, Guiyao
Zhou, Pan
Sun, Lichao
Chen, Yongchao
author_facet Zhou, Xueyang
Sun, Yihan
Gong, Xijie
Tie, Guiyao
Zhou, Pan
Sun, Lichao
Chen, Yongchao
contents Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time required for stages such as evaluation environment construction, trajectory collection, model training, and evaluation. To address this challenge, we propose a new paradigm for embodied AI development in which users express goals and constraints through conversation, and the system automatically plans and executes the development workflow. We instantiate this paradigm with EmbodiedClaw, a conversational agent that turns high-frequency, high-cost embodied research activities, including environment creation and revision, benchmark transformation, trajectory synthesis, model evaluation, and asset expansion, into executable skills. Experiments on end-to-end workflow tasks, capability-specific evaluations, human researcher studies, and ablations show that EmbodiedClaw reduces manual engineering effort while improving executability, consistency, and reproducibility. These results suggest a shift from manual toolchains to conversationally executable workflows for embodied AI development.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13800
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
Zhou, Xueyang
Sun, Yihan
Gong, Xijie
Tie, Guiyao
Zhou, Pan
Sun, Lichao
Chen, Yongchao
Robotics
I.2
Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time required for stages such as evaluation environment construction, trajectory collection, model training, and evaluation. To address this challenge, we propose a new paradigm for embodied AI development in which users express goals and constraints through conversation, and the system automatically plans and executes the development workflow. We instantiate this paradigm with EmbodiedClaw, a conversational agent that turns high-frequency, high-cost embodied research activities, including environment creation and revision, benchmark transformation, trajectory synthesis, model evaluation, and asset expansion, into executable skills. Experiments on end-to-end workflow tasks, capability-specific evaluations, human researcher studies, and ablations show that EmbodiedClaw reduces manual engineering effort while improving executability, consistency, and reproducibility. These results suggest a shift from manual toolchains to conversationally executable workflows for embodied AI development.
title EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
topic Robotics
I.2
url https://arxiv.org/abs/2604.13800