Awesome GitHub RepositoriesReasoning Optimization

DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing and internal monologues to solve complex mathematical and logical problems by breaking tasks into sequential, verifiable thought processes. The model is developed using reinforcement learning to optimize reasoning patterns and verify logical steps. It employs a distillation process to transfer these high-performance logic capabilities from a large teacher model into smaller, computationally efficient versions. The training framework incorporates group relative policy optimiz

This library provides a comprehensive framework for fine-tuning, aligning, and distilling transformer-based language models. It serves as a toolkit for adapting models to specialized domains through supervised learning, while offering advanced methodologies to improve output quality and reasoning capabilities. The project distinguishes itself through specialized alignment and optimization techniques, including direct preference optimization and reinforcement learning, which allow models to be tuned against human preferences without complex reward modeling. It further supports training efficie

VLM-R1 是一个推理视觉语言模型和具身智能框架，旨在将视觉输入和语言指令映射为物理导航路径点和机器人动作。它作为一个多模态策略优化器和开放词汇检测器，能够根据任意自然语言描述定位物体。 该系统的独特之处在于使用思维链推理和强化学习来解决复杂的视觉和空间任务。它利用视频语义记忆系统，该系统采用视觉缓存来维护实时视频历史记录，以实现低延迟交互和持续的时间推理。 该框架涵盖了广泛的功能，包括用于机器人导航的单目路径点映射、用于物体识别的区域标记定位，以及用于多模态推理稳定性的基于策略的监督微调。它还支持开放词汇检测、指代表达理解，以及通过视觉提示检索提取细粒度物体特征。 该项目使用 Python 实现，并支持在 Ascend 硬件上进行推理。

该项目是一个推理框架和代理编排器，实现了“思维树”（Tree of Thoughts）方法论，以提高大语言模型的逻辑输出。它作为一个基于搜索的问题求解器，将复杂任务表示为状态空间分支模型，其中离散的思维作为节点，逻辑转换作为边。 该系统协调多个模型代理来生成、评估和修剪候选解决方案。它采用深度优先搜索启发式算法和递归评估来探索多种推理路径，过滤掉低质量分支以迭代趋向于最优解。 该框架涵盖了推理优化和多代理编排方面的高级功能。它专注于将困难任务分解为候选思维，并通过迭代提示工程来优化语言模型的输出。

LLM-RL-Visualized 是一个视觉参考库和知识图谱集合，旨在解释大语言模型 (LLM) 和强化学习算法。它提供了一个结构化的概念图和分类系统，涵盖了语言模型对齐与强化学习的交叉领域。 该项目通过复杂工作流的详细视觉映射脱颖而出，例如在人类反馈强化学习 (RLHF) 中奖励模型与策略优化的协调。它对比了不同的偏好优化架构（如 RLHF 和直接偏好优化 DPO），并追溯了从马尔可夫决策过程到 Actor-Critic 框架的强化学习算法理论渊源。 该库涵盖了广泛的能力，包括 LLM 推理优化、参数高效微调技术，以及模型开发管道的顺序阶段。它还提供了模型配置的结构图、Token 解码策略的可视化，以及检索增强生成 (RAG) 和工具集成的操作流程。 其他内容包括神经网络基本操作的插图，以及蒙特卡洛树搜索和知识蒸馏等逻辑推理机制。

R1-V 是一套用于开发多模态模型的工具集，提供了一个低成本的训练环境，旨在优化大型视觉语言模型的推理和反馈循环。它集成了训练框架、微调流水线和性能评估工具。 该项目具有一个强化学习框架，通过基于视觉验证奖励正确输出来提高视觉推理和泛化能力。它还包括一个监督微调流水线，用于使用标记数据集和配置文件将视觉语言模型定制到特定任务。 该套件包含专门用于评估模型在计数和几何任务中性能的视觉推理评估工具和数据集。

simpleRL-reason is a training framework designed to improve mathematical and logical deduction in large language models. It utilizes reinforcement learning and policy optimization to enhance the accuracy and transparency of step-by-step deduction chains. The project implements a pipeline that establishes baseline capabilities through supervised fine-tuning before applying reinforcement learning to maximize deductive accuracy. It features a reward modeling toolkit that calculates scalar feedback by comparing generated reasoning steps against verified mathematical ground truths. The framework

OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca

This project is a technical resource and implementation guide for building transformer-based language model architectures and training pipelines from scratch. It focuses on the design of models capable of natural language processing, including the integration of pretrained weights and the creation of foundational model frameworks. The project specifically emphasizes logical reasoning and mathematical problem solving. It provides a framework for optimizing these capabilities through reinforcement learning and the use of automated verifiers to evaluate and reward correct reasoning paths. The r