Popular GitHub Repositories for Cot

Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 ?

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Syzygy-of-thoughts

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)

Research papers about Chain of Thought (CoT)

gpt-o1 like chain of thoughts with local LLMs in R

A no-string framework for reasoning over your tabular data rows with any provided LLM

[arXiv 2501.13117]The Multiplex CoT makes AI more thoughtful.

GPT Table Semantic Parsing with complex & non-intuitive structure.

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。

Deepseek-CoT

It is a dataset for fine-tuning LLM to solve 24(puzzle)

Experiments with reasoning models, training techniques, papers

Explore DeepSeek R1?: reproduction guides, papers, insightful tweets&blogs to explore and learn. ?

an approach to optimizing large language model (LLM) responses by extracting, reranking, and refining their internal chain-of-thought (CoT). By focusing on the most coherent and relevant parts of the CoT, we can minimize contradictory reasoning and potentially reduce token usage—ultimately leading to more reliable and efficient outputs.

The official code for CoT / ZSL reasoning framework ?, utilized in paper: "Large Language Models in Targeted Sentiment Analysis in Russian"