DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo

Hugging Face Daily Papers Papers

Summary

DexJoCo introduces a benchmark and toolkit for task-oriented dexterous manipulation in MuJoCo, featuring 11 functional tasks, a low-cost data collection system, and comprehensive evaluations that highlight limitations in current dexterous manipulation policies.

Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, existing dexterous benchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io
Original Article
View Cached Full Text

Cached at: 05/18/26, 06:24 AM

Paper page - DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo

Source: https://huggingface.co/papers/2605.16257 Published on May 15

#2 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

DexJoCo presents a benchmark and toolkit for dexterous manipulation with 11 functional tasks evaluating tool-use, bimanual coordination, and long-horizon execution, along with a low-cost data collection system and comprehensive model evaluation.

Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardizedbenchmarks for systematic evaluation. However, existing dexterousbenchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, abenchmarkandtoolkitfor task-orienteddexterous manipulation, comprising 11functionally grounded tasksthat evaluatetool-use,bimanual coordination,long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support fordomain randomizationto assess robustness. Webenchmarkmodern models under diverse settings, including visual anddynamics randomization,multi-task training, andaction-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies indexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io

View arXiv pageView PDFProject pageGitHub7Add to collection

Get this paper in your agent:

hf papers read 2605\.16257

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/2605.16257 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.16257 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.16257 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

MuJoCo – Advanced Physics Simulation

Hacker News Top

Google DeepMind maintains MuJoCo, a high-performance open-source physics engine with C/Python APIs and Unity plugin for robotics and ML research.

CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents

arXiv cs.AI

This paper introduces CoCoDA, a framework that uses a co-evolving compositional Directed Acyclic Graph (DAG) to manage tool libraries for augmented agents. It enables small language models to efficiently retrieve and compose tools, allowing an 8B model to match or exceed the performance of a 32B model on reasoning benchmarks.