{"name":"LLM Reasoners: Advanced Library for Large Language Model Reasoning","description":"LLM Reasoners is a powerful Python library designed to significantly enhance the complex reasoning capabilities of Large Language Models. It offers a comprehensive suite of cutting-edge search algorithms, intuitive visualization tools, and optimized performance for efficient LLM inference. The library prioritizes rigorous implementation and reproducibility, making it a reliable tool for researchers and developers in the AI field.","github":"https://github.com/maitrix-org/llm-reasoners","url":"https://osrepos.com/repo/maitrix-org-llm-reasoners","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/maitrix-org-llm-reasoners","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/maitrix-org-llm-reasoners.md","json":"https://osrepos.com/repo/maitrix-org-llm-reasoners.json","topics":["Python","LLM","Reasoning","AI","Machine Learning","NLP","Deep Learning","Algorithms"],"keywords":["Python","LLM","Reasoning","AI","Machine Learning","NLP","Deep Learning","Algorithms"],"stars":null,"summary":"LLM Reasoners is a powerful Python library designed to significantly enhance the complex reasoning capabilities of Large Language Models. It offers a comprehensive suite of cutting-edge search algorithms, intuitive visualization tools, and optimized performance for efficient LLM inference. The library prioritizes rigorous implementation and reproducibility, making it a reliable tool for researchers and developers in the AI field.","content":"## Introduction\n\nLLM Reasoners is an open-source Python library from Maitrix.org, dedicated to empowering Large Language Models (LLMs) with advanced reasoning abilities. It provides a structured framework for implementing and evaluating complex reasoning algorithms, abstracting them into key components: a world model, a search algorithm, and a reward function. This design allows users to easily experiment with and apply state-of-the-art reasoning techniques to various problems.\n\nThe library stands out for its collection of cutting-edge reasoning algorithms, including Reasoner Agent, Inference-time Scaling with PRM, Reasoning-via-Planning (MCTS), and Tree-of-Thoughts (BFS/DFS), among others. It also features an intuitive visualization tool that helps users understand the intricate reasoning processes, even for complex algorithms like Monte-Carlo Tree Search, with minimal code. Furthermore, LLM Reasoners is optimized for efficiency, integrating high-performance LLM inference frameworks like SGLang to accelerate advanced reasoning techniques. The project emphasizes rigorous implementation and reproducibility, ensuring that its algorithms are both theoretically sound and practically usable, as highlighted in its [COLM2024 paper](https://arxiv.org/abs/2404.05221 \"LLM Reasoners Paper\" target=\"_blank\").\n\n## Installation\n\nEnsure you are using Python 3.10 or later.\n\nbash\nconda create -n reasoners python=3.10\nconda activate reasoners\n\n\n**Install from `pip`**\n\nbash\npip install llm-reasoners\n\n\n**Install from GitHub**\n(Recommended if you want to run the examples in the GitHub repo)\n\nbash\ngit clone https://github.com/maitrix-org/llm-reasoners --recursive\ncd llm-reasoners\npip install -e .\n\n\nAdding `--recursive` will help you clone exllama and LLM-Planning automatically. Note that some other optional modules may require additional dependencies. Please refer to the error message for details.\n\n## Examples\n\nLLM Reasoners offers a clear and modular approach to implementing reasoning algorithms. The library abstracts an LLM reasoning algorithm into three key components: a *reward function*, a *world model*, and a *search algorithm*. Users define a `WorldModel` to handle initial states, state transitions, and terminal conditions, and a `SearchConfig` to specify actions and reward calculations. These are then combined with a `SearchAlgorithm` like MCTS to solve problems.\n\nThe repository's 'Quick Tour' provides a runnable example demonstrating how to solve BlocksWorld problems. This example illustrates how to define custom `WorldModel` and `SearchConfig` classes, and then apply a `SearchAlgorithm` to find optimal reasoning chains. A powerful visualization tool is also integrated, allowing users to easily diagnose and understand the reasoning process with just one line of Python code. You can explore a runnable notebook [here](https://github.com/maitrix-org/llm-reasoners/blob/main/demo.ipynb \"LLM Reasoners Demo Notebook\" target=\"_blank\").\n\n## Why Use LLM Reasoners?\n\nLLM Reasoners provides several compelling reasons for its adoption in projects requiring advanced LLM reasoning:\n\n*   **Cutting-Edge Reasoning Algorithms**: Access to a wide array of the most up-to-date search algorithms for reasoning with LLMs, including Reasoner Agent, Inference-time Scaling with PRM, Reasoning-via-Planning (MCTS), and Tree-of-Thoughts (BFS/DFS).\n*   **Intuitive Visualization and Interpretation**: The library includes a visualization tool that simplifies the understanding of complex reasoning processes, enabling users to diagnose and interpret algorithm behavior effortlessly.\n*   **Efficient Reasoning with LLMs**: Optimizes performance by integrating high-performance LLM inference frameworks like [SGLang](https://github.com/sgl-project/sglang \"SGLang GitHub Repo\" target=\"_blank\"), offering significant speed-ups and supporting various LLM backends.\n*   **Rigorous Implementation and Reproducibility**: Prioritizes precision and reliability, ensuring that implemented algorithms are faithful to their original formulations and performance, as demonstrated by successful reproductions of key research papers.\n*   **Active Development**: The project is continuously evolving, with recent updates including the integration of Deepseek R1, the introduction of **ReasonerAgent** (a fully open-source, web-browsing research agent), and enhanced planning algorithms for web environments.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/maitrix-org/llm-reasoners](https://github.com/maitrix-org/llm-reasoners \"LLM Reasoners GitHub Repository\" target=\"_blank\")\n*   **Official Website**: [https://www.llm-reasoners.net/](https://www.llm-reasoners.net/ \"LLM Reasoners Official Website\" target=\"_blank\")\n*   **Paper (COLM2024)**: [https://arxiv.org/abs/2404.05221](https://arxiv.org/abs/2404.05221 \"LLM Reasoners Paper\" target=\"_blank\")\n*   **Discord**: [https://discord.gg/PxDJby9W](https://discord.gg/PxDJby9W \"LLM Reasoners Discord\" target=\"_blank\")\n*   **Maitrix.org**: [https://maitrix.org/](https://maitrix.org/ \"Maitrix.org Website\" target=\"_blank\")","metrics":{"detailViews":2,"githubClicks":1},"dates":{"published":null,"modified":"2026-02-02T16:01:19.000Z"}}