Search Results for "reasoning" - Page 4
Sort By:
Showing 605 open source projects for "reasoning"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
All Agentic Architectures
Implementation of 17+ agentic architectures
...Each architecture is explained through runnable notebooks that illustrate how the agent works internally and how it interacts with tools, data sources, or other agents. The repository organizes the architectures into a structured learning path that progresses from simple reasoning agents to complex multi-agent systems. Examples include planning agents, tool-using agents, tree-of-thought reasoning systems, and collaborative multi-agent environments. -
2
LLM Agents Papers
Must-read Papers on LLM Agents
LLM Agent Papers is an open-source repository that curates research papers related to large language model agents and autonomous AI systems. The project organizes academic literature that explores how language models can act as agents capable of reasoning, planning, and interacting with external tools or environments. Rather than providing software code, the repository functions as a structured knowledge base that helps researchers navigate the rapidly expanding field of agent-based AI research. Papers are categorized into thematic groups covering topics such as tool use, planning algorithms, reasoning strategies, and multi-agent collaboration. ... -
3
Kimi k1.5
Scaling Reinforcement Learning with LLMs
...Kimi-k1.5 is trained jointly on text and vision data, giving it true multimodal reasoning capabilities where it can interpret and generate content across modalities in a unified way. -
4
Quint Code
Structured reasoning framework for Claude Code, Gemini, and Cursor
Quint Code is a structured reasoning and decision-support framework aimed at making AI-assisted software engineering and decision workflows more rigorous and auditable. It implements the First Principles Framework (FPF) to guide users and AI tools through hypothesis generation, logical verification, evidence gathering, and documented decision making, reducing reliance on ad hoc or “vibe” coding. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
DeepSeek Coder V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models
DeepSeek-Coder-V2 is the version-2 iteration of DeepSeek’s code generation models, refining the original DeepSeek-Coder line with improved architecture, training strategies, and benchmark performance. While the V1 models already targeted strong code understanding and generation, V2 appears to push further in both multilingual support and reasoning in code, likely via architectural enhancements or additional training objectives. The repository provides updated model weights, evaluation results on benchmarks (e.g. HumanEval, MultiPL-E, APPS), and new inference/serving scripts. Compared to the original, DeepSeek-Coder-V2 likely incorporates improved context management, caching strategies, or enhanced infilling capabilities. ... -
6
SocratiCode
Enterprise-grade (40m+ LOC) codebase intelligence
...It encourages critical thinking by asking structured questions that lead developers toward discovering solutions on their own. The system is designed to improve understanding of programming concepts through iterative reasoning and dialogue. It can be used to practice coding challenges, debug logic, and explore design decisions in a guided manner. SocratiCode emphasizes learning through inquiry rather than passive consumption of solutions. It is particularly valuable for students and self-learners aiming to deepen conceptual understanding. The project reflects a pedagogical shift toward interactive and reflective coding education. -
7
R1-V
Witness the aha moment of VLM with less than $3
R1-V is an initiative aimed at enhancing the generalization capabilities of Vision-Language Models (VLMs) through Reinforcement Learning in Visual Reasoning (RLVR). The project focuses on building a comprehensive framework that emphasizes algorithm enhancement, efficiency optimization, and task diversity to achieve general vision-language intelligence and visual/GUI agents. The team's long-term goal is to contribute impactful open-source research in this domain. -
8
Tianji
Evaluation suite designed to assess the performance of LLMs
Tianji is a comprehensive evaluation suite designed to assess the performance of large language models (LLMs) across multiple dimensions. It focuses on measuring general capabilities such as reasoning, knowledge, commonsense, and language understanding. Tianji provides a curated set of benchmarks and a unified framework for systematically comparing LLMs, making it useful for research and model selection. -
9
MiniCPM4
Ultra-Efficient LLMs on End Device
MiniCPM4 is part of the MiniCPM family of ultra-efficient large language models designed specifically for high performance on edge devices and resource-constrained environments. Unlike traditional large-scale models that require extensive computational resources, MiniCPM4 focuses on delivering competitive reasoning and language capabilities while maintaining significantly lower latency and higher efficiency. It achieves this through optimized architectures, scalable training strategies, and techniques such as long-context pretraining and YaRN-based length extension, allowing it to handle sequences up to 128K tokens effectively. The model demonstrates strong performance across tasks such as long-text comprehension, reasoning, and general language generation, often outperforming similar-sized models in both speed and accuracy. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
verl-agent
Designed for training LLM/VLM agents via RL
...Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
11
LongBench
LongBench v2 and LongBench (ACL 25'&24')
...LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. The benchmark includes multiple categories such as single-document question answering, multi-document reasoning, summarization, long dialogue understanding, and code analysis. It supports bilingual evaluation in English and Chinese to assess multilingual capabilities across extended contexts. Newer versions of the benchmark introduce extremely long context windows ranging from thousands to millions of tokens, enabling researchers to test the limits of modern long-context models. -
12
ControlFlow
Take control of your AI agents
...The framework provides a structured approach for building AI systems by breaking complex tasks into smaller units called tasks that can be assigned to specialized AI agents. Developers can combine these tasks into flows that define how work is executed, enabling the creation of multi-step reasoning pipelines and collaborative agent systems. ControlFlow focuses on maintaining transparency and control in AI applications by providing explicit workflow structures instead of opaque chains of prompts. The system integrates with common LLM providers and allows developers to create workflows that blend traditional software logic with AI-driven reasoning. -
13
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
...By testing models across diverse scenarios, the benchmark highlights strengths and weaknesses in reasoning, long-term planning, and tool usage. -
14
DeepSearcher
Open Source Deep Research Alternative to Reason and Search
...It also supports flexible embeddings, making it easier to choose different embedding models depending on domain requirements, latency targets, or accuracy goals. The overall workflow aims to minimize hallucinations by grounding outputs in retrieved material and then applying structured reasoning over that evidence before generating a final report. -
15
Hello-Agents
Building an Intelligent Agent from Scratch
Hello Agents is an open educational project designed to teach developers how to understand, design, and build AI-native agents from the ground up through structured tutorials and practical examples. The project focuses on guiding learners beyond superficial framework usage toward deeper comprehension of agent architecture, reasoning loops, and real-world implementation patterns. It walks users through core concepts such as ReAct-style reasoning, tool usage, memory handling, and multi-step task execution, enabling hands-on experimentation with modern LLM-powered agent systems. The repository is structured as a progressive learning path, combining theory, exercises, and runnable code so users can incrementally build more capable agents. ... -
16
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
...It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
17
Step3-VL-10B
Multimodal model achieving SOTA performance
...Despite having only about 10 billion parameters, it delivers performance that rivals or even surpasses much larger models (10×–20× larger) on a wide range of multimodal benchmarks covering reasoning, perception, and complex tasks, positioning it as one of the most powerful models in its class. It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
18
Granite 3.0 Language Models
New set of lightweight state-of-the-art, open foundation models
This repository introduces Granite 3.0 language models as lightweight, state-of-the-art open foundation models built to natively support multilinguality, coding, reasoning, and tool usage. A central goal is efficient deployment, including the potential to run on constrained compute resources while remaining useful for a broad span of enterprise tasks. The repo positions the models for both research and commercial use under an Apache-2.0 license, signaling permissive adoption paths. Documentation highlights the capability mix (reasoning, tool use, code) and points to model artifacts and guidance for evaluation. ... -
19
Code World Model (CWM)
Research code artifacts for Code World Model (CWM)
...Inference scripts and utilities for code generation tasks. Evaluation benchmarks on code, mathematics, and reasoning tasks. Demos, serving code, and evaluation pipelines. -
20
Rapid LaTeX OCR
Formula recognition based on LaTeX-OCR and ONNXRuntime
Formula recognition based on LaTeX-OCR and ONNXRuntime. rapid_latex_ocr is a tool to convert formula images to latex format. The reasoning code in the repo is modified from LaTeX-OCR, the model has all been converted to ONNX format, and the reasoning code has been simplified, Inference is faster and easier to deploy. The repo only has codes based on ONNXRuntime or OpenVINO inference in onnx format and does not contain training model codes. If you want to train your own model, please move to LaTeX-OCR. ... -
21
Lean 4
Lean 4 programming language and theorem prover
Lean 4 is both a programming language and an interactive theorem prover, designed to support formal reasoning while also functioning as an efficient and extensible general-purpose language. The project serves researchers, mathematicians, programmers, and formal methods users who need a system for writing machine-checked proofs as well as executable programs in the same environment. One of its defining characteristics is its emphasis on extensibility, since Lean 4 is built to allow users to develop custom automation, metaprogramming tools, and domain-specific extensions instead of being limited to a fixed proving workflow. ... -
22
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
23
Semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
Semantica is an open-source graph-native infrastructure layer for building explainable and auditable AI systems. It ingests fragmented data, extracts meaningful entities and relationships, and transforms them into context and knowledge graphs. Deterministic reasoning, ontology management, provenance tracking, and decision records help explain how conclusions were reached. The platform can complement existing LLMs, vector databases, and agent frameworks rather than replacing them. It supports RDF and labeled-property graphs along with standards-oriented interoperable storage. A browser-based Knowledge Explorer provides graph visualization, temporal inspection, and causal-chain tracing. ... -
24
Computational Thinking
Introduction to computational thinking with Julia
...It emphasizes learning how to translate problems into computational terms and developing algorithms and models to analyze them effectively. Using Julia, the course highlights both mathematical reasoning and practical coding, bridging the gap between theory and application. The materials include lectures, notebooks, exercises, and projects that encourage experimentation and discovery. By combining programming with conceptual depth, the repository aims to build skills that are transferable across disciplines and essential for modern scientific inquiry. -
25
Fulcro
A library for development of single-page full-stack web applications
Fulcro is a batteries-included, full-stack library for building data-driven web applications in Clojure and ClojureScript. It integrates seamlessly with React, supports web, native, and desktop (Electron) targets, and enables strong local reasoning while facilitating rapid development and scalable production-level UIs. The rewrite of Fulcro Inspect is available via the releases page of Fulcro Inspect. And there are preliminary instructions for using it with the latest Fulcro. The alpha versions of Fulcro 3.8 are alpha purely because of this development-time change and its potential issues, and are otherwise production-ready.