[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。

LLM面试常见手撕合集

收集为大模型面试准备的手撕代码

The agent that grows with you

Tools for checking ACL paper submissions

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

The open source coding agent.

deepclaw，一个开源的 agent/rag 脚手架

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

Deep Reinforcement Learning

The batteries-included agent harness.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

DeepAgentForce 是以 Hermes 的核心思想为灵魂、建在标准开源栈上的多租户生产级平台，可扩展性和部署能力远超 Hermes。

预训练模型泛化能力挑战 第一名开源代码

Public repository for Agent Skills

A simple, easy-to-hack GraphRAG implementation

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

OpenAI Router 轻量级、持久化、零配置的 OpenAI API 统一网关

Build Real-Time Knowledge Graphs for AI Agents

Open source annotation tool for machine learning practitioners.

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Source code for the paper "C-LLM: Learn to Check Chinese Spelling Errors Character by Character"

A Step-by-Step Implementation of Qwen 3 MoE Architecture from Scratch