verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Agent S: an open agentic framework that uses computers like a human

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Official code repo for the paper "MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments"

Memory_Driven_GUI_Agent

A curated collection of resources, tools, and frameworks for developing GUI Agents.

Large language model review prompts

[AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding

RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

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

DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

Solve Visual Understanding with Reinforced VLMs

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

[AAAI-2026] Code for "UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning"

Mobile-Agent: The Powerful GUI Agent Family

[AAAI 2026]Release of code, datasets and model for our work TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents

ZeroGUI: Automating Online GUI Learning at Zero Human Cost

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

Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Elevate your AI research writing, no more tedious polishing ✨

The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

Edit Banana: A framework for converting statistical formats into editable.

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation.

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

Agent Skills as a Memory Layer

A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.