MintAct: A Unified Visual Agent for Digital Environments

arXiv:2609.22083 · cs.CV · Submitted 2026-09-18 · Read on arXiv

cs.CV

Submitted: 2026-09-18

Updated: 2026-09-18

Code: https://github.com/kakaobrain/coyo-dataset

Terminology

• Grounding — 65× in this paper · explained in 3 episodes
• Visual Tool Use — 31× in this paper
• Reinforcement Learning — 21× in this paper · explained in 4 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Trace — 12× in this paper · explained in 2 episodes
• Action Space — 8× in this paper · explained in 1 episode
• Ablation — 7× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Benchmarking — 5× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Credit assignment — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Agent Interactions — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents
• Qwen3-VL Technical Report
• SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
• MolmoPoint: Better Pointing for VLMs with Grounding Tokens
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
• AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
• iOSWorld: A Benchmark for Personally Intelligent Phone Agents
• Weblica: Scalable and Reproducible Training Environments for Visual Web Agents
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
• Understanding R1-Zero-Like Training: A Critical Perspective
• MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
• UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Magistral
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
• Agents' Last Exam
• InSTA: Towards Internet-Scale Training For Agents
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
• MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models