lgy0404/LearnAct
Official code repo for the paper "LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark"
This project helps researchers and developers create AI agents that can automate tasks on mobile applications more effectively. It uses human demonstrations of a task on a mobile app as input to teach the AI agent how to perform similar tasks, even on apps it hasn't seen before. The output is an AI agent capable of executing complex workflows on various mobile Graphical User Interfaces (GUIs).
No commits in the last 6 months.
Use this if you are a researcher or developer focused on building robust mobile GUI automation agents and need a comprehensive dataset and framework for demonstration-based learning.
Not ideal if you are an end-user looking for a ready-to-use mobile automation tool for personal or business tasks, as this is a research framework.
Stars
46
Forks
—
Language
Python
License
—
Category
Last pushed
May 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/lgy0404/LearnAct"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...