A flexible, efficient, and production-ready post-training reinforcement learning framework for LLMs

OtherDeep LearningMultimodal

VIEW DETAILS →

An RL training environment building library for LLMs, providing complete infrastructure from development and testing to scaled rollout collection, with built-in RLVR scenarios and tool-calling support.

OtherDeep LearningAI Agents

VIEW DETAILS →

An open-source framework for building, evaluating, and training general multi-agent systems. Features natural language agent creation, distributed reinforcement learning training pipeline, and complex environment interactions. Ranks top on authoritative benchmarks including GAIA, OSWorld, and VisualWebArena.

OtherMultimodalLarge Language Models

VIEW DETAILS →

A generative agent framework inspired by human dual-process theory, combining fast and slow thinking mechanisms with in-context reinforcement learning to efficiently solve complex interactive reasoning tasks.

OtherLarge Language ModelsReinforcement Learning

VIEW DETAILS →

An LLM post-training framework for RL scaling by Tsinghua THUDM, deeply integrating Megatron-LM training with SGLang inference engine for distributed reinforcement learning on large models like GLM, Qwen, DeepSeek, and Llama.

OtherDeep LearningLarge Language Models

VIEW DETAILS →

AI-Compass is a comprehensive open-source project that provides learning paths and practical guidelines for AI technologies, helping users from beginners to professionals build a complete AI knowledge system from fundamental theory to cutting-edge applications.

Docs, Tutorials & ResourcesPythonNext.js

VIEW DETAILS →

A curated collection of autonomous agents (LLM) research papers updated daily, providing the latest AI research findings for researchers and developers。

Docs, Tutorials & ResourcesPythonLangChain

VIEW DETAILS →

Odyssey is a framework that empowers LLM-based Minecraft agents with open-world skills, featuring 40 primitive skills and 183 compositional skills, enabling AI to autonomously explore, learn, and execute diverse tasks in the Minecraft universe.

Agent & ToolingPythonLangChain

VIEW DETAILS →

A curated collection of recent research papers on autonomous agents, focusing on both reinforcement learning-based and large language model-based approaches, helping researchers quickly understand the cutting edge of the field。

Docs, Tutorials & ResourcesPythonPyTorch

VIEW DETAILS →

Trinity-RFT is a general-purpose, flexible and user-friendly framework for LLM reinforcement fine-tuning (RFT). It decouples RFT into three coordinated components: Explorer, Trainer, and Buffer, enabling users with different backgrounds to train LLM-powered agents for specific domains.

Model & Inference FrameworkPythonPyTorch

VIEW DETAILS →