CoAct-1: Computer-using Agents with Coding as Actions
Paper
•
2508.03923
•
Published
•
14
TOREAD: c/bua
Note quick done
The Unreasonable Effectiveness of Scaling Agents for Computer Use
Paper • 2510.02250 • Published • 24Note quick done
Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution
Paper • 2509.21072 • Published • 15Note quick done: bullshit
Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent
Paper • 2509.17917 • PublishedNote quick done: train Qwen2.5-VL
ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
Paper • 2509.21823 • Published • 1Note quick done
-
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
Paper • 2508.14040 • Published • 2 -
SEA: Self-Evolution Agent with Step-wise Reward for Computer Use
Paper • 2508.04037 • Published