
Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
Stars: 1441

This repository contains a collection of awesome resources for reinforcement learning in language models. It includes tutorials, code implementations, research papers, and tools to help researchers and practitioners explore and apply reinforcement learning techniques in natural language processing tasks. Whether you are a beginner or an expert in the field, this repository aims to provide valuable insights and guidance to enhance your understanding and implementation of reinforcement learning in language models.
README:
We welcome everyone to open an issue for any related work we havenβt discussed, and weβll try to address it in the next release!
- [2025-09-18] π We update the full list of papers in the category structure of the survey!
- [2025-09-12] π Our survey was ranked #1 Paper of the Day on π€ Hugging Face Daily Papers!
- [2025-09-11] π₯ Excited to release our RL for LRMs Survey! Weβll be updating the full list of papers in with a new category structure soon. Check it out: Paper.
- [2025-08-15] π₯ Introducing SSRL: an investigation for Agentic Search RL without reliance on external search engine. Check it out: GitHub and Paper.
- [2025-05-27] π₯ Introducing MARTI: A Framework for LLM-based Multi-Agent Reinforced Training and Inference. Check it out: Github.
- [2025-04-23] π₯ Introducing TTRL: an open-source solution for online RL on data without ground-truth labels, especially test data. Check it out: Github and Paper.
- [2025-03-20] π₯ We are excited to introduce collection of papers and projects on RL for reasoning models!
- A Survey of Reinforcement Learning for Large Reasoning Models
- π News
- π Contents
- πΊοΈ Overview
-
π Paper List
- Frontier Models
- Reward Design
- Policy Optimization
- Sampling Strategy
-
Training Resource
- Static Corpus (Code)
- Static Corpus (STEM)
- Static Corpus (Math)
- Static Corpus (Agent)
- Static Corpus (Mix)
- Dynamic Environment (Rule-based)
- Dynamic Environment (Code-based)
- Dynamic Environment (Game-based)
- Dynamic Environment (Model-based)
- Dynamic Environment (Ensemble-based)
- RL Infrastructure (Primary)
- RL Infrastructure (Secondary)
- Applications
- π Acknowledgment
- π Citation
- Star History
Our survey provides a comprehensive examination of Reinforcement Learning for Large Reasoning Models.
We organize the survey into five main sections:
- Foundational Components: Reward design, policy optimization, and sampling strategies
- Foundational Problems: Key debates and challenges in RL for LRMs
- Training Resources: Static corpora, dynamic environments, and infrastructure
- Applications: Real-world implementations across diverse domains
- Future Directions: Emerging research opportunities and challenges
This survey is extended and refined from the original Awesome RL Reasoning Recipes repo. We are deeply grateful to all contributors for their efforts, and we sincerely thank for their all interest in Awesome RL Reasoning Recipes. The contents of the previous repository are available here.
If you find this survey helpful, please cite our work:
@article{zhang2025survey,
title={A Survey of Reinforcement Learning for Large Reasoning Models},
author={Zhang, Kaiyan and Zuo, Yuxin and He, Bingxiang and Sun, Youbang and Liu, Runze and Jiang, Che and Fan, Yuchen and Tian, Kai and Jia, Guoli and Li, Pengfei and others},
journal={arXiv preprint arXiv:2509.08827},
year={2025}
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for Awesome-RL-for-LRMs
Similar Open Source Tools

Awesome-RL-for-LRMs
This repository contains a collection of awesome resources for reinforcement learning in language models. It includes tutorials, code implementations, research papers, and tools to help researchers and practitioners explore and apply reinforcement learning techniques in natural language processing tasks. Whether you are a beginner or an expert in the field, this repository aims to provide valuable insights and guidance to enhance your understanding and implementation of reinforcement learning in language models.

phoenix
Phoenix is a tool that provides MLOps and LLMOps insights at lightning speed with zero-config observability. It offers a notebook-first experience for monitoring models and LLM Applications by providing LLM Traces, LLM Evals, Embedding Analysis, RAG Analysis, and Structured Data Analysis. Users can trace through the execution of LLM Applications, evaluate generative models, explore embedding point-clouds, visualize generative application's search and retrieval process, and statistically analyze structured data. Phoenix is designed to help users troubleshoot problems related to retrieval, tool execution, relevance, toxicity, drift, and performance degradation.

Hands-On-Large-Language-Models-CN
Hands-On Large Language Models CN(ZH) is a Chinese version of the book 'Hands-On Large Language Models' by Jay Alammar and Maarten Grootendorst. It provides detailed code annotations and additional insights, offers Notebook versions suitable for Chinese network environments, utilizes openbayes for free GPU access, allows convenient environment setup with vscode, and includes accompanying Chinese language videos on platforms like Bilibili and YouTube. The book covers various chapters on topics like Tokens and Embeddings, Transformer LLMs, Text Classification, Text Clustering, Prompt Engineering, Text Generation, Semantic Search, Multimodal LLMs, Text Embedding Models, Fine-tuning Models, and more.

Hands-On-LangChain-for-LLM-Applications-Development
Practical LangChain tutorials for developing LLM applications, including prompt templates, output parsing, chatbots memory, chains, evaluating applications, building agents using LangChain & OpenAI API, retrieval augmented generation with LangChain, documents loading, splitting, vector database & text embeddings, information retrieval, answering questions from documents, chat with files, and introduction to Open AI function calling.

cgft-llm
The cgft-llm repository is a collection of video tutorials and documentation for implementing large models. It provides guidance on topics such as fine-tuning llama3 with llama-factory, lightweight deployment and quantization using llama.cpp, speech generation with ChatTTS, introduction to Ollama for large model deployment, deployment tools for vllm and paged attention, and implementing RAG with llama-index. Users can find detailed code documentation and video tutorials for each project in the repository.

Hands-On-LLM-Applications-Development
Hands-On-LLM-Applications-Development is a repository focused on developing applications using Large Language Models (LLMs). The repository provides hands-on tutorials, guides, and resources for building various applications such as LangChain for LLM applications, Retrieval Augmented Generation (RAG) with LangChain, building LLM agents with LangGraph, and advanced LangChain with OpenAI. It covers topics like prompt engineering for LLMs, building applications using HuggingFace open-source models, LLM fine-tuning, and advanced RAG applications.

Steel-LLM
Steel-LLM is a project to pre-train a large Chinese language model from scratch using over 1T of data to achieve a parameter size of around 1B, similar to TinyLlama. The project aims to share the entire process including data collection, data processing, pre-training framework selection, model design, and open-source all the code. The goal is to enable reproducibility of the work even with limited resources. The name 'Steel' is inspired by a band 'δΈθ½ιεΉ΄ζ εΊ' and signifies the desire to create a strong model despite limited conditions. The project involves continuous data collection of various cultural elements, trivia, lyrics, niche literature, and personal secrets to train the LLM. The ultimate aim is to fill the model with diverse data and leave room for individual input, fostering collaboration among users.

InternVL
InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM. It is a vision-language foundation model that can perform various tasks, including: **Visual Perception** - Linear-Probe Image Classification - Semantic Segmentation - Zero-Shot Image Classification - Multilingual Zero-Shot Image Classification - Zero-Shot Video Classification **Cross-Modal Retrieval** - English Zero-Shot Image-Text Retrieval - Chinese Zero-Shot Image-Text Retrieval - Multilingual Zero-Shot Image-Text Retrieval on XTD **Multimodal Dialogue** - Zero-Shot Image Captioning - Multimodal Benchmarks with Frozen LLM - Multimodal Benchmarks with Trainable LLM - Tiny LVLM InternVL has been shown to achieve state-of-the-art results on a variety of benchmarks. For example, on the MMMU image classification benchmark, InternVL achieves a top-1 accuracy of 51.6%, which is higher than GPT-4V and Gemini Pro. On the DocVQA question answering benchmark, InternVL achieves a score of 82.2%, which is also higher than GPT-4V and Gemini Pro. InternVL is open-sourced and available on Hugging Face. It can be used for a variety of applications, including image classification, object detection, semantic segmentation, image captioning, and question answering.

Firefly
Firefly is an open-source large model training project that supports pre-training, fine-tuning, and DPO of mainstream large models. It includes models like Llama3, Gemma, Qwen1.5, MiniCPM, Llama, InternLM, Baichuan, ChatGLM, Yi, Deepseek, Qwen, Orion, Ziya, Xverse, Mistral, Mixtral-8x7B, Zephyr, Vicuna, Bloom, etc. The project supports full-parameter training, LoRA, QLoRA efficient training, and various tasks such as pre-training, SFT, and DPO. Suitable for users with limited training resources, QLoRA is recommended for fine-tuning instructions. The project has achieved good results on the Open LLM Leaderboard with QLoRA training process validation. The latest version has significant updates and adaptations for different chat model templates.

oumi
Oumi is an open-source platform for building state-of-the-art foundation models, offering tools for data preparation, training, evaluation, and deployment. It supports training and fine-tuning models with various parameters, working with text and multimodal models, synthesizing and curating training data, deploying models efficiently, evaluating models comprehensively, and running on different platforms. Oumi provides a consistent API, reliability, and flexibility for research purposes.

haystack-core-integrations
This repository contains integrations to extend the capabilities of Haystack version 2.0 and onwards. The code in this repo is maintained by deepset, see each integration's `README` file for details around installation, usage and support.

LLMs-Zero-to-Hero
LLMs-Zero-to-Hero is a repository dedicated to training large language models (LLMs) from scratch, covering topics such as dense models, MOE models, pre-training, supervised fine-tuning, direct preference optimization, reinforcement learning from human feedback, and deploying large models. The repository provides detailed learning notes for different chapters, code implementations, and resources for training and deploying LLMs. It aims to guide users from being beginners to proficient in building and deploying large language models.

awesome-ai-painting
This repository, named 'awesome-ai-painting', is a comprehensive collection of resources related to AI painting. It is curated by a user named η§ι£, who is an AI painting enthusiast with a background in the AIGC industry. The repository aims to help more people learn AI painting and also documents the user's goal of creating 100 AI products, with current progress at 4/100. The repository includes information on various AI painting products, tutorials, tools, and models, providing a valuable resource for individuals interested in AI painting and related technologies.

LLMs
LLMs is a Chinese large language model technology stack for practical use. It includes high-availability pre-training, SFT, and DPO preference alignment code framework. The repository covers pre-training data cleaning, high-concurrency framework, SFT dataset cleaning, data quality improvement, and security alignment work for Chinese large language models. It also provides open-source SFT dataset construction, pre-training from scratch, and various tools and frameworks for data cleaning, quality optimization, and task alignment.
For similar tasks

LLM-PlayLab
LLM-PlayLab is a repository containing various projects related to LLM (Large Language Models) fine-tuning, generative AI, time-series forecasting, and crash courses. It includes projects for text generation, sentiment analysis, data analysis, chat assistants, image captioning, and more. The repository offers a wide range of tools and resources for exploring and implementing advanced AI techniques.

Awesome-RL-for-LRMs
This repository contains a collection of awesome resources for reinforcement learning in language models. It includes tutorials, code implementations, research papers, and tools to help researchers and practitioners explore and apply reinforcement learning techniques in natural language processing tasks. Whether you are a beginner or an expert in the field, this repository aims to provide valuable insights and guidance to enhance your understanding and implementation of reinforcement learning in language models.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

LocalAI
LocalAI is a free and open-source OpenAI alternative that acts as a drop-in replacement REST API compatible with OpenAI (Elevenlabs, Anthropic, etc.) API specifications for local AI inferencing. It allows users to run LLMs, generate images, audio, and more locally or on-premises with consumer-grade hardware, supporting multiple model families and not requiring a GPU. LocalAI offers features such as text generation with GPTs, text-to-audio, audio-to-text transcription, image generation with stable diffusion, OpenAI functions, embeddings generation for vector databases, constrained grammars, downloading models directly from Huggingface, and a Vision API. It provides a detailed step-by-step introduction in its Getting Started guide and supports community integrations such as custom containers, WebUIs, model galleries, and various bots for Discord, Slack, and Telegram. LocalAI also offers resources like an LLM fine-tuning guide, instructions for local building and Kubernetes installation, projects integrating LocalAI, and a how-tos section curated by the community. It encourages users to cite the repository when utilizing it in downstream projects and acknowledges the contributions of various software from the community.

AiTreasureBox
AiTreasureBox is a versatile AI tool that provides a collection of pre-trained models and algorithms for various machine learning tasks. It simplifies the process of implementing AI solutions by offering ready-to-use components that can be easily integrated into projects. With AiTreasureBox, users can quickly prototype and deploy AI applications without the need for extensive knowledge in machine learning or deep learning. The tool covers a wide range of tasks such as image classification, text generation, sentiment analysis, object detection, and more. It is designed to be user-friendly and accessible to both beginners and experienced developers, making AI development more efficient and accessible to a wider audience.

glide
Glide is a cloud-native LLM gateway that provides a unified REST API for accessing various large language models (LLMs) from different providers. It handles LLMOps tasks such as model failover, caching, key management, and more, making it easy to integrate LLMs into applications. Glide supports popular LLM providers like OpenAI, Anthropic, Azure OpenAI, AWS Bedrock (Titan), Cohere, Google Gemini, OctoML, and Ollama. It offers high availability, performance, and observability, and provides SDKs for Python and NodeJS to simplify integration.

jupyter-ai
Jupyter AI connects generative AI with Jupyter notebooks. It provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in JupyterLab and the Jupyter Notebook. Specifically, Jupyter AI offers: * An `%%ai` magic that turns the Jupyter notebook into a reproducible generative AI playground. This works anywhere the IPython kernel runs (JupyterLab, Jupyter Notebook, Google Colab, Kaggle, VSCode, etc.). * A native chat UI in JupyterLab that enables you to work with generative AI as a conversational assistant. * Support for a wide range of generative model providers, including AI21, Anthropic, AWS, Cohere, Gemini, Hugging Face, NVIDIA, and OpenAI. * Local model support through GPT4All, enabling use of generative AI models on consumer grade machines with ease and privacy.

langchain_dart
LangChain.dart is a Dart port of the popular LangChain Python framework created by Harrison Chase. LangChain provides a set of ready-to-use components for working with language models and a standard interface for chaining them together to formulate more advanced use cases (e.g. chatbots, Q&A with RAG, agents, summarization, extraction, etc.). The components can be grouped into a few core modules: * **Model I/O:** LangChain offers a unified API for interacting with various LLM providers (e.g. OpenAI, Google, Mistral, Ollama, etc.), allowing developers to switch between them with ease. Additionally, it provides tools for managing model inputs (prompt templates and example selectors) and parsing the resulting model outputs (output parsers). * **Retrieval:** assists in loading user data (via document loaders), transforming it (with text splitters), extracting its meaning (using embedding models), storing (in vector stores) and retrieving it (through retrievers) so that it can be used to ground the model's responses (i.e. Retrieval-Augmented Generation or RAG). * **Agents:** "bots" that leverage LLMs to make informed decisions about which available tools (such as web search, calculators, database lookup, etc.) to use to accomplish the designated task. The different components can be composed together using the LangChain Expression Language (LCEL).
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.