The benchmark of the ACL 2026 paper "WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments".
☆25May 11, 2026Updated 6 months ago
Alternatives and similar repositories for WindowsWorld
Users that are interested in WindowsWorld are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code of our paper "A Unified Agentic Framework for Evaluating Conditional Image Generation".☆32Jul 22, 2025Updated last year
- Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard …☆73Aug 3, 2026Updated 3 months ago
- ☆33Updated this week
- UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience☆84Apr 3, 2026Updated 7 months ago
- Recursive Self-Improvement Personal Assistant☆481Aug 26, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents☆229Aug 13, 2026Updated 3 months ago
- Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)☆40Jun 29, 2026Updated 4 months ago
- The official implementation of the work "Can Indirect Prompt Injection Attacks Be Detected and Removed?"☆11Dec 25, 2025Updated 10 months ago
- This project page is about the pytorch code implementation of GlyphBERT by the HITsz-TMG research group.☆11Aug 29, 2022Updated 4 years ago
- ☆10Dec 5, 2024Updated last year
- [ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents☆49Apr 7, 2026Updated 7 months ago
- ☆51Feb 10, 2026Updated 9 months ago
- [EMNLP 2026] WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces☆174Aug 22, 2026Updated 2 months ago
- Gym-Anything: Turn any Software into an Agent Environment☆306Oct 27, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The diverse video evaluation benchmark☆15Oct 12, 2026Updated last month
- The benchmark and datasets of the ICML 2024 paper "VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual C…☆17May 27, 2024Updated 2 years ago
- A multimodal context reasoning approach that introduce the multi-view semantic alignment information via prefix tuning.☆16Sep 14, 2023Updated 3 years ago
- ☆10Sep 16, 2026Updated last month
- OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks☆421Updated this week
- Code and data of WSDM 2023 paper "Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark".☆24Jun 1, 2023Updated 3 years ago
- CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents☆84Sep 3, 2026Updated 2 months ago
- ☆23Apr 11, 2026Updated 7 months ago
- (ICLR 2026)Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’☆59Jan 26, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ChronoQA - A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation☆21Dec 26, 2025Updated 10 months ago
- 用 Blender 白模控制 AI 视频生成的机位、空间与切点 —— 在花钱之前把错误拦下来。A Blender greybox previz harness for AI video generation: camera, space and cut timing as …☆18Aug 11, 2026Updated 3 months ago
- Matlab code of LRTCFPan☆10Apr 19, 2026Updated 6 months ago
- Controllable Animation Video Generation with Large Models-based Multimodal Agents☆265Jan 7, 2026Updated 10 months ago
- The model, data and code for OpenMobile☆53Jul 9, 2026Updated 4 months ago
- a novel self-evolving paradigm, without task, reward, or complex workflow☆35May 12, 2026Updated 6 months ago
- Extract deeplinks, shortcuts, and external entry points from Android APK/XAPK files.☆13May 11, 2026Updated 6 months ago
- [ECCV 2026] MoKus: This repo is the official implementation of "MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Conc…☆14Jun 19, 2026Updated 4 months ago
- GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding☆12May 27, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- EmojiNotion – project for CBMI 2025 conference☆14Jun 6, 2025Updated last year
- [CVPR25 Highlight] A ChatGPT-Prompted Visual hallucination Evaluation Dataset, featuring over 100,000 data samples and four advanced eval…☆34Apr 16, 2025Updated last year
- Implementation of AAAI-2025 paper -- "CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation"☆13Jan 14, 2025Updated last year
- ☆20Updated this week
- Code for CVPR 2019 paper☆12Apr 26, 2019Updated 7 years ago
- Code for paper https://arxiv.org/abs/2501.00522☆15Apr 28, 2025Updated last year
- A real-world mobile-agent evaluation framework.☆11Mar 30, 2026Updated 7 months ago
Are these results useful?