GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning
GTAGym turns GTA V-inspired missions into a verifiable benchmark and RL environment, revealing where visual agents still fail at dynamic control.
ls ./papers | grep "#Computer-use agents"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
4 papers · #Computer-use agents
GTAGym turns GTA V-inspired missions into a verifiable benchmark and RL environment, revealing where visual agents still fail at dynamic control.
Microsoft’s Mage-VL-Cowork trains a 4B computer-use agent to combine GUI actions, code, and terminal tools through evolved harnesses and a five-stage curriculum.
RETRACE shows why computer-use agents need more than reflection or restart: recovery must restore a functionally equivalent state, and weak recovery can worsen failures.
NorthCUA combines executable tasks, persistent computer-use environments, verified trajectories, staged learning, and reinforcement learning to improve long-horizon desktop and web agents.