arXiv Computer Vision
MintAct: A Unified Visual Agent for Digital Environments
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 15
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
arXiv:2603. 18464v3 Announce Type: replace Abstract: Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models is severely bottlenecked by synchronization barriers and the high cost of environment data acquisition.
arXiv Machine Learning
Sep 15
GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
arXiv AI
Oct 16
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
MAI-Gym is an open, all-in-one platform that unifies GUI agent evaluation, data collection, and online reinforcement learning training across mobile, computer, and web environments. It supports ten established benchmarks, scales to 20,000 parallel environment instances, and enables automated synthesis of diverse GUI applications and tasks with execution-validated verifiers. Using this platform, the authors trained a 9B-parameter agent, MAI-Gym-9B, achieving state‑of‑the‑art performance on MobileWorld and OSWorld-Verified, and demonstrated that training on a mocked train‑ticketing app improves real‑world task success from 28.8% to 48.1% on a physical phone.
arXiv AI
Sep 7
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
RL-VLA$^3$ is a fully asynchronous distributed reinforcement learning framework designed for Vision‑Language‑Action (VLA) model training. It allows fine‑grained asynchronous interaction between simulation, inference, and training via dynamic batching schedulers and flexible environment sharding, addressing the variable, resource‑intensive latencies of physical simulators. Experiments across multiple simulation backends, VLA architectures, and RL algorithms show throughput gains of up to 85.2% over synchronous baselines while preserving sample efficiency, and the system scales from 8 to 256 GPUs.
Hugging Face Trending Papers
Aug 24
GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data s...
arXiv AI
Aug 25
GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
arXiv:2608.22847v1 Announce Type: new Abstract: Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottl...