RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures

Hugging Face Daily Papers Papers

Summary

RoboTALES introduces a two-stage framework combining LLM-based planning and VLM-based criticism to improve task-aligned video generation and robotic policy training, significantly outperforming existing methods on long-horizon manipulation tasks.

Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these models can be difficult to use for planning or policy extraction. To address these limitations, we propose RoboTALES, a single-stage framework that learns task-aligned simulated futures and uses them to train robot policies. Our approach introduces two key innovations: (1) a hierarchical LLM-based planner that breaks complex tasks into a sequence of subgoals to guide the model's imagination; and (2) a VLM-based critic that evaluates these ``imagined'' futures and uses reward-based feedback to keep the model's internal representations focused on the goal. By anchoring the video generator in abstract reasoning, we produce temporally consistent rollouts and more coherent actions. We evaluate RoboTALES on diverse manipulation tasks from RoboCasa and LIBERO10, and show that our method consistently outperforms existing methods, especially in long-horizon tasks. Our code and models are publicly available at https://github.com/hananshafi/RoboTALES.
Original Article
View Cached Full Text

Cached at: 07/09/26, 11:41 PM

Paper page - RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures

Source: https://huggingface.co/papers/2607.06018

Abstract

RoboTALES introduces a two-stage framework that combines LLM-based planning and VLM-based criticism to improve task-aligned video generation and robotic policy training.

Pretrainedvideo generative modelsare promising backbones forvisuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these models can be difficult to use for planning or policy extraction. To address these limitations, we propose RoboTALES, a single-stage framework that learnstask-aligned simulated futuresand uses them to trainrobot policies. Our approach introduces two key innovations: (1) ahierarchical LLM-based plannerthat breaks complex tasks into a sequence of subgoals to guide the model’s imagination; and (2) aVLM-based criticthat evaluates these ``imagined’’ futures and uses reward-based feedback to keep the model’s internal representations focused on the goal. By anchoring the video generator in abstract reasoning, we produce temporally consistent rollouts and more coherent actions. We evaluate RoboTALES on diverse manipulation tasks from RoboCasa and LIBERO10, and show that our method consistently outperforms existing methods, especially inlong-horizon tasks. Our code and models are publicly available at https://github.com/hananshafi/RoboTALES.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2607\.06018

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

Models citing this paper1

#### hanangani/robotales-ckpts Updatedabout 1 hour ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.06018 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.06018 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

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

Hugging Face Daily Papers

RoboLab is a high-fidelity simulation benchmarking framework for evaluating task-generalist robotic policies, introducing the RoboLab-120 benchmark with 120 tasks across visual, procedural, and relational competency axes. It enables scalable, realistic task generation and systematic analysis of policy behavior under controlled perturbations to assess true generalization capabilities.