microsoft / WindowsAgentArena
Windows Agent Arena (WAA) πͺ is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
β557Updated last month
Alternatives and similar repositories for WindowsAgentArena:
Users that are interested in WindowsAgentArena are comparing it to the libraries listed below
- Agent S: an open agentic framework that uses computers like a humanβ749Updated this week
- Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhanβ¦β548Updated 7 months ago
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agentsβ242Updated last week
- AWM: Agent Workflow Memoryβ231Updated last month
- Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"β521Updated 10 months ago
- Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactionβ175Updated this week
- β342Updated this week
- agent q - oss advanced reasoning and learning for autonomous ai agentsβ383Updated 3 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RLβ282Updated 3 weeks ago
- This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.β177Updated 2 weeks ago
- β560Updated this week
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and β¦β331Updated 7 months ago
- π€ Agent-as-a-Judge and DevAI datasetβ308Updated 3 weeks ago
- Search-o1: Agentic Search-Enhanced Large Reasoning Modelsβ335Updated this week
- Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-apiβ978Updated this week
- Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.β841Updated this week
- ππͺ BrowserGym, a Gym environment for web task automationβ477Updated this week
- Agentlessπ±: an agentless approach to automatically solve software development problemsβ1,281Updated 3 weeks ago
- [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multβ¦β686Updated this week
- β433Updated 3 months ago
- CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/β206Updated last month
- β291Updated 9 months ago
- π» A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.β428Updated this week
- UGround: Universal GUI Visual Grounding for GUI Agentsβ138Updated this week
- A compilation of the best multi-agent papersβ341Updated last week
- Task-based Agentic Framework using StrictJSON as the coreβ442Updated last week
- Automated Design of Agentic Systemsβ1,135Updated last week
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reβ¦β189Updated this week
- Environments, tools, and benchmarks for general computer agentsβ188Updated 2 months ago
- Autonomous Agents (LLMs) research papers. Updated Daily.β606Updated this week