MintAct: A Unified Visual Agent for Digital Environments

Hugging Face Daily Papers Papers

Summary

MintAct is a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool use, achieving state-of-the-art performance on various benchmarks.

We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool use, trained at 2B, 4B, and 8B scales. Through careful design of our environments, data, and training recipes, MintAct models match the performance of per-domain specialists across all of these capabilities. To enable this, we develop a scalable environment and reinforcement learning (RL) infrastructure. On the environment side, we host hundreds of concurrent instances across heterogeneous per-domain backends, serving both trajectory data collection and online RL. To enable efficient and scalable RL training, an asynchronous framework keeps explicit control over the cross-domain training distribution and remains stable under noisy environment feedback and off-policy drift. Experimental results show that MintAct achieves state-of-the-art performance (48.9 on OSWorld-Verified) across a wide range of benchmarks at comparable model sizes.
Original Article
View Cached Full Text

Cached at: 09/21/26, 03:20 AM

Paper page - MintAct: A Unified Visual Agent for Digital Environments

Source: https://huggingface.co/papers/2609.22083 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

WepresentMintAct,afamilyofvision-languagemodelsthatunifiesUIgrounding,multi-stepnavigationacrossmobile,desktop,andweb,andvisualtooluse,trainedat2B,4B,and8Bscales.Throughcarefuldesignofourenvironments,data,andtrainingrecipes,MintActmodelsmatchtheperformanceofper-domainspecialistsacrossallofthesecapabilities.Toenablethis,wedevelopascalableenvironmentandreinforcementlearning(RL)infrastructure.Ontheenvironmentside,wehosthundredsofconcurrentinstancesacrossheterogeneousper-domainbackends,servingbothtrajectorydatacollectionandonlineRL.ToenableefficientandscalableRLtraining,anasynchronousframeworkkeepsexplicitcontroloverthecross-domaintrainingdistributionandremainsstableundernoisyenvironmentfeedbackandoff-policydrift.ExperimentalresultsshowthatMintActachievesstate-of-the-artperformance(48.9onOSWorld-Verified)acrossawiderangeofbenchmarksatcomparablemodelsizes.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.22083

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/2609.22083 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.22083 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.22083 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

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

arXiv cs.AI

MIRAGE is a framework for mobile GUI agents that replaces verbose chain-of-thought reasoning with compact continuous latent representations, incorporating a generative world model perspective to predict future screen states before acting. On AndroidWorld and AndroidControl benchmarks, it achieves competitive or superior performance while reducing generated tokens by over 75%.

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Papers with Code Trending

The MAI-UI technical report presents a family of foundation GUI agents in multiple sizes, addressing real-world deployment challenges with a self-evolving data pipeline, device-cloud collaboration, and online RL, achieving state-of-the-art results on GUI grounding and mobile navigation benchmarks.

UI-Venus-2 Technical Report

Hugging Face Daily Papers

UI-Venus-2 is an open-source multimodal GUI agent designed for digital automation across mobile, web, and desktop environments, using unified reasoning-action loops and robust verification to enable reliable real-world applications.