reasoning

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Hierarchical Reasoning Model Official Release

Graph-Native Infrastructure for Context and Accountable AI Systems

A visual playground for agentic workflows: Iterate over your agents 10x faster

Implement a reasoning LLM in PyTorch from scratch, step by step

TypeDB: Built for systems, not records

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Awesome Reasoning LLM Tutorial/Survey/Guide

A Survey of Reinforcement Learning for Large Reasoning Models

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.

Fully open data curation for reasoning models

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

Scalable RL solution for advanced reasoning of language models

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

A collection of AI Agents papers (Updated biweekly)

Protege Desktop

[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.

The MATH Dataset (NeurIPS 2021)

An Open-sourced Knowledgable Large Language Model Framework.

A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"

Latest Advances on System-2 Reasoning

Understanding R1-Zero-Like Training: A Critical Perspective