Stars
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
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"
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
Build Real-Time Knowledge Graphs for AI Agents
A modular graph-based Retrieval-Augmented Generation (RAG) system
Official code of "RoboOmni: Proactive Robot Manipulation in Omni-modal Context"
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
MiniMax-M2, a model built for Max coding & agentic workflows.
Pokee Deep Research Model Open Source Repo
DeepAnalyze is the first agentic LLM for autonomous data science.
MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
Official Implementation of Knowledge Flow Prompting
Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
A Survey of Reinforcement Learning for Large Reasoning Models