MintAct: A Unified Visual Agent for Digital Environments
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.
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
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
UI-Mate is a foundation GUI agent that uses environment-grounded training and in-context demonstrations to improve reliability on long-horizon office tasks, achieving state-of-the-art results on computer-use benchmarks.
MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
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
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.
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
MAG introduces a benchmark and harness for multimodal web agents that both execute tasks and generate step-by-step guide text, using screenshots and grounding schemes. The work includes a GRPO training method that nearly doubles the success rate of a 9B agent.
UI-Venus-2 Technical Report
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.