GitHub topics: reasoning-models
lee-messi/RM-IAT
Replication Materials for "Implicit Bias-Like Patterns in Reasoning Models"
Language: Jupyter Notebook - Size: 7 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 2 - Forks: 0
Abhisang3/xVerify
xVerify: Efficient Answer Verifier for Large Language Model Evaluations
Language: Python - Size: 806 KB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 0 - Forks: 1
eric-ai-lab/Soft-Thinking
Official implementation of the paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"
Language: Python - Size: 4.41 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 217 - Forks: 16
microsoft/DSP-Plus
Implementation and subsequent optimization for "Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models"
Language: Python - Size: 1.32 MB - Last synced at: 6 days ago - Pushed at: 3 months ago - Stars: 20 - Forks: 2
Zefan-Cai/R-KV
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Language: Python - Size: 55.2 MB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 1,105 - Forks: 178
mohammad-gh009/DrugReasoner
Predicting drug approval with reasoning.
Language: Python - Size: 136 MB - Last synced at: 11 days ago - Pushed at: 12 days ago - Stars: 2 - Forks: 0
dialexity/dialectical-framework
Turn stories, strategies, or systems into insight. Auto-generate Dialectical Wheels (DWs) from any text to reveal blind spots, surface polarities, and trace dynamic paths toward synthesis. DWs are semantic maps that expose tension, transformation, and coherence within a system—whether narrative, ethical, organizational, or technological.
Language: Python - Size: 6.3 MB - Last synced at: 11 days ago - Pushed at: 12 days ago - Stars: 8 - Forks: 5
zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Language: Python - Size: 16.8 MB - Last synced at: 15 days ago - Pushed at: about 2 months ago - Stars: 6,836 - Forks: 672
ariannamethod/ARIANNA-CHAIN
The chain of Arianna. Resonating and Reasoning Model.
Language: Python - Size: 1.24 MB - Last synced at: 17 days ago - Pushed at: 17 days ago - Stars: 2 - Forks: 0
DevEvil-AI/Nexus-AI
A simple AI source code that includes chat, reasoning and image features using public APIs like xAI, OpenAI, HuggingFace and Flux.
Language: JavaScript - Size: 24.4 KB - Last synced at: 29 days ago - Pushed at: 29 days ago - Stars: 4 - Forks: 1
likhonsdev/GenZ
This repository contains the code for training and deploying the GenZ model. The process is fully automated using GitHub Actions.
Language: JavaScript - Size: 611 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0
microsoft/BUILD25-LAB333
This repository hosts the instructions and workshop materials for Lab 333 - Evaluate Reasoning Models for Your Generative AI Solutions
Language: Jupyter Notebook - Size: 4.75 MB - Last synced at: 6 days ago - Pushed at: 4 months ago - Stars: 18 - Forks: 17
kaicheng001/Awesome-R1
A curated list of research papers, models, and resources related to R1-style reasoning models following DeepSeek-R1's breakthrough in January 2025.
Size: 57.6 KB - Last synced at: 7 days ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0
nimishbongale/nimible-researcher
For quick yet deep research on any topic, use this Nimble Researcher. It will generate a response and improve it based on automated feedback until it meets the requirements.
Language: Python - Size: 23.4 KB - Last synced at: about 1 month ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0
codelion/pts
Pivotal Token Search
Language: Python - Size: 692 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 111 - Forks: 7
UKPLab/acl2025-diverse-cot
Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"
Language: Python - Size: 20.3 MB - Last synced at: about 2 months ago - Pushed at: 2 months ago - Stars: 29 - Forks: 3
yongchao98/R1-Code-Interpreter
R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning
Size: 973 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 14 - Forks: 2
Abishk-developer/kv
Modern remote KVM solution with minimal setup. Stream video and audio, send input from SBCs, and expose disk images easily. 🌐💻
Language: Crystal - Size: 86.9 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0
sinanuozdemir/oreilly-agi
Explore the evolution of AGI through historical context, reasoning models, and agent systems, while gaining hands-on experience with cutting-edge models like Claude 4, DeepSeek-R1, and OpenAI's o3. Learn to critically evaluate AGI benchmarks, understand their limitations, and identify where current models excel or struggle in reasoning tasks.
Language: Jupyter Notebook - Size: 351 KB - Last synced at: about 2 months ago - Pushed at: 3 months ago - Stars: 12 - Forks: 5
czg1225/VeriThinker
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
Language: Python - Size: 2.47 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 47 - Forks: 1
MiniMax-AI/MiniMax-M1
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
Language: Python - Size: 7.1 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 2,513 - Forks: 190
OpenSPG/KAG-Thinker
An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.
Language: Python - Size: 29.3 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 15 - Forks: 0
UCSC-VLAA/MedReason
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Language: Python - Size: 4.66 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 177 - Forks: 16
AbhaySingh71/AI-Lawyer-RAG-with-Deepseek
AI Lawyer is an intelligent reasoning legal assistant powered by DeepSeek , Ollama RAG and LangChain, designed to streamline legal research and document analysis. By leveraging retrieval-augmented generation (RAG), it provides precise legal insights, and contract summarization. With an intuitive Streamlit-based UI, analyze legal documents.
Language: Python - Size: 1.15 MB - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 9 - Forks: 3
silentghost2/Using-machine-learning-model-to-detect-bias-correction-of-papers-
This is an ;emi completed evaluation software which is based upon the question paper pattern of certain university. which is going to be intregrated with ML to detect the bias correction and help evaluators
Language: HTML - Size: 44.9 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0
MicDZ/MANBench
MANBench: Is Your Multimodal Model Smarter than Human?
Language: Python - Size: 22.9 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 2 - Forks: 0
aygp-dr/illusion-of-thinking
Project exploring Apple's 'The Illusion of Thinking' research paper on LRM limitations
Language: Scheme - Size: 13.7 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0
IAAR-Shanghai/xVerify
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Language: Python - Size: 826 KB - Last synced at: 3 months ago - Pushed at: 5 months ago - Stars: 109 - Forks: 7
hao-ai-lab/Dynasor
Simple extension on vLLM to help you speed up reasoning model without training.
Language: Python - Size: 11.8 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 152 - Forks: 23
fscdc/ReasonMap
ReasonMap
Language: Python - Size: 7.45 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 2 - Forks: 0
DolbyUUU/Sudoku4LLM
Sudoku4LLM is a Sudoku dataset generator for training and evaluating reasoning in Large Language Models (LLMs). It offers customizable puzzles, difficulty levels, and 11 serialization formats to support structured data reasoning and Chain of Thought (CoT) experiments.
Language: Python - Size: 29.3 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 4 - Forks: 0
KazKozDev/net-reflective-reasoning-llm
LLM reasoning method: combining reflexive cueing with real-time web search and multi-stage analysis for more accurate and explainable answers.
Language: Python - Size: 18.9 MB - Last synced at: 3 months ago - Pushed at: 5 months ago - Stars: 2 - Forks: 1
nitya/model-mondays Fork of microsoft/model-mondays
Model Mondays is a weekly livestreamed series on Microsoft Reactor that helps you make informed model choice decisions with timely updates and model deep-dives. Watch live for the content. Join Discord for the discussions.
Language: Jupyter Notebook - Size: 6.73 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 1 - Forks: 0
DolbyUUU/DeepEnlighten
Pure RL without SFT to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
Language: Python - Size: 21.6 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 1 - Forks: 0
DolbyUUU/Logic-RL-Lite
Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".
Language: Python - Size: 14.8 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 3 - Forks: 0
mrorigo/agentic-deep-graph-reasoning
Agentic Deep Graph Reasoning Implementation
Language: Python - Size: 1.77 MB - Last synced at: 5 months ago - Pushed at: 6 months ago - Stars: 12 - Forks: 1
akhilpandey95/s1
Experiments on test-time scaling approaches for reasoning LM's to enforce better <think> or <wait> capabilities.
Language: Jupyter Notebook - Size: 12.7 KB - Last synced at: 5 months ago - Pushed at: 7 months ago - Stars: 1 - Forks: 0
sshh12/state-sandbox
State Sandbox is an experimental game for socioeconomic simulation. It uses Large Language Models (o3-mini) to simulate the world and complex policy impacts.
Language: JavaScript - Size: 2.06 MB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 3 - Forks: 0
