InfiXAI/InfiGUI-G1
[AAAI 2026 Oral] Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy Optimization (AEPO) to overcome semantic alignment bottlenecks in GUI agents through efficient, guided exploration.
InfiGUI-G1 improves how AI agents understand and interact with graphical user interfaces (GUIs). It takes natural language instructions and a GUI screenshot, then identifies the correct UI element to interact with, even for complex or subtly described actions. This is for AI researchers and developers building sophisticated GUI automation or AI assistants.
137 stars.
Use this if you are developing AI agents that need to reliably interpret natural language commands and pinpoint the correct elements on any graphical interface, like a website or desktop application.
Not ideal if you are looking for an off-the-shelf end-user application for GUI automation, as this project provides the underlying models and training framework.
Stars
137
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/InfiXAI/InfiGUI-G1"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AMA-CMFAI/LAMBDA
This is the offical repository of paper "LAMBDA: A large Model Based Data Agent"....
zjunlp/LLMAgentPapers
Must-read Papers on LLM Agents.
hyp1231/awesome-llm-powered-agent
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
MineDojo/Voyager
An Open-Ended Embodied Agent with Large Language Models
wadeKeith/Awesome-Embodied-AI
An Introduction to Embodied Intelligence (A Quick Guide of Embodied-AI) (Updating)