Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

GUI Grounding for Professional High-Resolution Computer Use

Python code for several metrics: PSNR, SSIM, UCIQE and UIQM

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay

Enable AI to control your PC. This repo includes the WorldGUI Benchmark and GUI-Thinker Agent Framework.

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

[TMLR'25] "Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents"

[NeurIPS 2025]"Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning"

Repository for the paper "InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners"

An awesome repository that maps the current landscape of GUI/OS Agent research

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Official implementation of UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning

This is a script for batch evaluation of psnr and ssim indicators of reconstructed images. It is suitable for image compression, image restoration, super-resolution reconstruction, image denoising …

[SIGIR 2024] TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

[AAAI 2023 Oral] Official code for "PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction".

R-HORIZON: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?

[ICML 2025] Improving Planning of Agents for Long-Horizon Tasks