Vesta: A Generalist Embodied Reasoning Model

Hugging Face Daily Papers Papers

Summary

Vesta is a unified embodied generalist model that integrates localization, spatial reasoning, navigation, and long-horizon planning into a single foundation model, outperforming specialized models by over 20% on benchmarks and over 35% on real-world robotic tasks.

Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at individual tasks, deploying a multi-model stack is computationally expensive and prone to cascading errors. We present Vesta, a unified embodied generalist that consolidates these capabilities into a single foundation model. Our approach combines a diverse and massive curated corpus designed to induce spatial grounding and a simple multimodal memory harness that enables reasoning over extended time horizons. Across diverse benchmarks, Vesta on average beats individual SOTA baselines by >20% and beats an ensemble of per-category-best baselines by >10% -- thus demonstrating that a generalist model can match or exceed specialists. On real-world robotic tasks requiring memory and reasoning, Vesta improves task success by >35\%. Our work thus demonstrates that a single generalist is a feasible, scalable, and arguably preferable alternative to combining specialists.
Original Article
View Cached Full Text

Cached at: 06/30/26, 03:34 AM

Paper page - Vesta: A Generalist Embodied Reasoning Model

Source: https://huggingface.co/papers/2606.20905 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Vesta is a unified embodied generalist model that integrates localization, spatial reasoning, navigation, and long-horizon planning into a single foundation model, outperforming specialized models in both benchmark tests and real-world robotic applications.

Robots operating in open-world environments must seamlessly integratelocalization,spatial reasoning, navigation, andlong-horizon planning. While specialist models excel at individual tasks, deploying a multi-model stack is computationally expensive and prone to cascading errors. We present Vesta, a unifiedembodied generalistthat consolidates these capabilities into a singlefoundation model. Our approach combines a diverse and massive curated corpus designed to inducespatial groundingand a simplemultimodal memoryharness that enables reasoning over extended time horizons. Across diverse benchmarks, Vesta on average beats individual SOTA baselines by >20% and beats an ensemble of per-category-best baselines by >10% -- thus demonstrating that a generalist model can match or exceed specialists. On real-world robotic tasks requiring memory and reasoning, Vesta improves task success by >35\%. Our work thus demonstrates that a single generalist is a feasible, scalable, and arguably preferable alternative to combining specialists.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.20905

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/2606.20905 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.20905 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.20905 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

VESTA: Visual Exploration with Statistical Tool Agents

arXiv cs.AI

This paper introduces VESTA, a framework that equips vision-language models with dynamically growing toolkits for data exploration and statistical model refinement, outperforming prior agent-based methods on complex scientific modeling tasks. The authors also present Dawn, a benchmark for distribution fitting and time series modeling, including real-world astronomy challenges.

World Value Models for Robotic Manipulation

Hugging Face Daily Papers

The paper presents World Value Model (WVM), a generalist robotic value model that combines world models with value estimation to accurately assess task progression and improve robotic policy learning from mixed-quality data, achieving state-of-the-art results on standard benchmarks and a new suboptimal data benchmark.

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models

Papers with Code Trending

This paper uncovers that prolonged reasoning in vision-language models can impair perceptual grounding, causing recognition failures on basic visual questions. It proposes Vision-Anchored Policy Optimization (VAPO) to steer reasoning toward visually grounded trajectories, achieving state-of-the-art performance with the VAPO-Thinker-7B model.