Signals 4 · free daily AI digest

MintAct: A Unified Visual Agent for Digital Environments

Paper recorded by Signals 4 on 2026-09-18 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21

Category: cs.CV · 计算机视觉 · first seen 2026-09-21

Abstract

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 e

Read on arXiv →

#16 most recent of 270 cs.CV papers we have recorded · ↑ newer: Virtual neural networks: hundreds of souls in a body · ↓ older: OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-
Cite this page: MintAct: A Unified Visual Agent for Digital Environments: the #16 most recent of 270 cs.CV papers we have recorded (as of 2026-09-18). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/mintact-a-unified-visual-agent-for-digital-environments.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions