#Reasoning

Showing 60 of 98 repositories tagged #reasoning, ranked by stars

VectifyAI
VectifyAI
PageIndex

πŸ“‘ PageIndex: Document Index for Vectorless, Reasoning-based RAG

Score
100
β˜… 33.9k β‘‚ 3.0k +12/day
Python
sapientinc
sapientinc
HRM

Hierarchical Reasoning Model Official Release

Score
83
β˜… 12.6k β‘‚ 1.8k +1/day
Python
PySpur-Dev
PySpur-Dev
pyspur

A visual playground for agentic workflows: Iterate over your agents 10x faster

Score
67
β˜… 5.7k β‘‚ 428 +4/day
TypeScript
rasbt
rasbt
reasoning-from-scratch

Implement a reasoning LLM in PyTorch from scratch, step by step

Score
50
β˜… 4.7k β‘‚ 705 +22/day
Jupyter Notebook
typedb
typedb
typedb

TypeDB: Built for systems, not records

Score
100
β˜… 4.4k β‘‚ 368 +7/day
Rust
ysymyth
ysymyth
ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

Score
80
β˜… 4.0k β‘‚ 385 +6/day
Jupyter Notebook
atfortes
atfortes
Awesome-LLM-Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 πŸ“

Score
100
β˜… 3.6k β‘‚ 212 +3/day
SkyworkAI
SkyworkAI
Skywork-R1V

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Score
95
β˜… 3.2k β‘‚ 281 +1/day
Python
TsinghuaC3I
TsinghuaC3I
Awesome-RL-for-LRMs

A Survey of Reinforcement Learning for Large Reasoning Models

Score
91
β˜… 2.5k β‘‚ 131 +1/day
TeX
amazon-science
amazon-science
auto-cot

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

Score
74
β˜… 2.0k β‘‚ 189 β€”
Jupyter Notebook
PRIME-RL
PRIME-RL
PRIME

Scalable RL solution for advanced reasoning of language models

Score
73
β˜… 1.9k β‘‚ 116 β€”
Python
onestardao
onestardao
WFGY

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

Score
98
β˜… 1.8k β‘‚ 163 +1/day
Jupyter Notebook
masamasa59
masamasa59
ai-agent-papers

A collection of AI Agents papers (Updated biweekly)

Score
97
β˜… 1.5k β‘‚ 117 +8/day
semantica-agi
semantica-agi
semantica

Semantica 🧠 β€’ Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI.

Score
100
β˜… 1.4k β‘‚ 200 +1/day
Python
zjunlp
zjunlp
KnowLM

An Open-sourced Knowledgable Large Language Model Framework.

Score
100
β˜… 1.4k β‘‚ 133 β€”
Python
m0n0x41d
m0n0x41d
haft

Engineering decisions engine that know when they're stale. Frame, compare, decide β€” with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.

Score
100
β˜… 1.4k β‘‚ 102 +5/day
Go
weitianxin
weitianxin
Awesome-Agentic-Reasoning

A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"

Score
94
β˜… 1.3k β‘‚ 102 +4/day
sail-sg
sail-sg
understand-r1-zero

Understanding R1-Zero-Like Training: A Critical Perspective

Score
71
β˜… 1.3k β‘‚ 60 +3/day
Python
RUC-NLPIR
RUC-NLPIR
Search-o1

πŸ” Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]

Score
82
β˜… 1.2k β‘‚ 106 +2/day
Python
PRIME-RL
PRIME-RL
TTRL

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

Score
92
β˜… 1.1k β‘‚ 82 +3/day
Python
zjunlp
zjunlp
Prompt4ReasoningPapers

[ACL 2023] Reasoning with Language Model Prompting: A Survey

Score
67
β˜… 1.0k β‘‚ 68 β€”
lasgroup
lasgroup
SDPO

Reinforcement Learning via Self-Distillation (SDPO)

Score
33
β˜… 993 β‘‚ 116 +5/day
Python
brylevkirill
brylevkirill
notes

Learn about Machine Learning and Artificial Intelligence

Score
90
β˜… 929 β‘‚ 239 β€”
plastic-labs
plastic-labs
tutor-gpt

AI tutor powered by Theory-of-Mind reasoning

Score
86
β˜… 912 β‘‚ 97 β€”
TypeScript
madaan
madaan
self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

Score
64
β˜… 809 β‘‚ 68 +1/day
Python
DavidZWZ
DavidZWZ
Awesome-Deep-Research

[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources

Score
88
β˜… 794 β‘‚ 64 +6/day
NucleoidAI
NucleoidAI
Nucleoid

Logic Language for LLMs πŸŒ±πŸ‹πŸŒ Build Neuro-Symbolic AI for Learning and Reasoning

Score
0
β˜… 756 β‘‚ 31 +1/day
Python
sail-sg
sail-sg
oat

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Score
77
β˜… 664 β‘‚ 63 β€”
Python
litexlang
litexlang
golitex

Litex: The Language Where Mathematics Verifies Itself.

Score
0
β˜… 659 β‘‚ 8 β€”
Rust
reasoning-survey
reasoning-survey
Awesome-Reasoning-Foundation-Models

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Score
59
β˜… 657 β‘‚ 61 +2/day
alexiglad
alexiglad
EBT

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

Score
83
β˜… 638 β‘‚ 89 β€”
Python
sunrainyg
sunrainyg
RandOpt

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

Score
89
β˜… 623 β‘‚ 68 +4/day
Python
math-ai-org
math-ai-org
mathcode

MathCode: A Frontier Mathematical Coding Agent

Score
85
β˜… 577 β‘‚ 59 β€”
Shell
jeffhj
jeffhj
LM-reasoning

This repository contains a collection of papers and resources on Reasoning in Large Language Models.

Score
56
β˜… 572 β‘‚ 37 β€”
RManLuo
RManLuo
reasoning-on-graphs

Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"

Score
58
β˜… 521 β‘‚ 65 β€”
Python
NVlabs
NVlabs
GDPO

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Score
79
β˜… 487 β‘‚ 32 +7/day
Python
TheAgenticAI
TheAgenticAI
CortexON

Open-source generalized AI agent for everyday task automations.

Score
0
β˜… 455 β‘‚ 78 β€”
Python
DavidZWZ
DavidZWZ
Awesome-RAG-Reasoning

[EMNLP 2025] Awesome RAG Reasoning Resources

Score
76
β˜… 448 β‘‚ 37 +1/day
PRIME-RL
PRIME-RL
Entropy-Mechanism-of-RL

The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.

Score
50
β˜… 443 β‘‚ 15 β€”
Python
zjunlp
zjunlp
EasyInstruct

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

Score
52
β˜… 407 β‘‚ 36 β€”
Python
JIA-Lab-research
JIA-Lab-research
Step-DPO

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Score
45
β˜… 398 β‘‚ 16 β€”
Python
TIGER-AI-Lab
TIGER-AI-Lab
MAmmoTH

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]

Score
48
β˜… 384 β‘‚ 46 β€”
Jupyter Notebook
yeahhe365
yeahhe365
Prisma

基于 Gemini ηš„ε―θ§†εŒ–ε€šζ™Ίθƒ½δ½“ζ·±εΊ¦ζŽ¨η†εΌ•ζ“Ž | A visual multi-agent deep reasoning engine powered by Gemini, featuring dynamic planning, chain-of-thought visualization, and multi-session management. Built with React 19 + TypeScript + Vite 6.

Score
80
β˜… 336 β‘‚ 32 +1/day
TypeScript
LAMDA-NeSy
LAMDA-NeSy
Awesome-LLM-Reasoning-with-NeSy

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

Score
70
β˜… 314 β‘‚ 22 +2/day
zjunlp
zjunlp
KnowAgent

[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

Score
60
β˜… 259 β‘‚ 21 β€”
Python
RManLuo
RManLuo
graph-constrained-reasoning

Official Implementation of ICML 2025 Paper: "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".

Score
36
β˜… 254 β‘‚ 30 +1/day
Python
stalkermustang
stalkermustang
llm-bulls-and-cows-benchmark

A mini-framework for evaluating LLM performance on the Bulls and Cows number guessing game, supporting multiple LLM providers.

Score
33
β˜… 234 β‘‚ 1 β€”
HTML
tongye98
tongye98
Awesome-Code-Benchmark

A comprehensive code domain benchmark review of LLM researches.

Score
60
β˜… 231 β‘‚ 17 +1/day
shure-dev
shure-dev
Awesome-LLM-Papers-Comprehensive-Topics

Awesome LLM Papers and repos on very comprehensive topics.

Score
35
β˜… 222 β‘‚ 23 β€”
lucidrains
lucidrains
tiny-recursive-model

Unofficial implementation of Tiny Recursive Model (TRM), improvement to HRM from Sapient AI, by Alexia Jolicoeur-Martineau

Score
80
β˜… 189 β‘‚ 34 +2/day
Python
lucidrains
lucidrains
coconut-pytorch

Implementation of πŸ₯₯ Coconut, Chain of Continuous Thought, in Pytorch

Score
40
β˜… 183 β‘‚ 8 β€”
Python
IAAR-Shanghai
IAAR-Shanghai
ICSFSurvey

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevationπŸ“ and hallucination alleviationπŸ„.

Score
30
β˜… 173 β‘‚ 5 β€”
Jupyter Notebook
zjunlp
zjunlp
LightThinker

[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression

Score
70
β˜… 163 β‘‚ 6 β€”
Python
mahmoudrabie
mahmoudrabie
agentic-ai

Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

Score
68
β˜… 154 β‘‚ 4 +1/day
Sreyan88
Sreyan88
GAMA

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

Score
29
β˜… 153 β‘‚ 15 β€”
Python
ThHanke
ThHanke
ontosphere

Browser-based RDF/ontology knowledge graph editor β€” load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clustering. AI-native via MCP tool surface and relay bridge. Fully client-side, no backend required.

Score
40
β˜… 150 β‘‚ 25 +5/day
TypeScript
logikon-ai
logikon-ai
awesome-deliberative-prompting

Awesome deliberative prompting: How to ask LLMs to produce reliable reasoning and make reason-responsive decisions.

Score
26
β˜… 125 β‘‚ 8 β€”
zhenyi4
zhenyi4
codi

Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"

Score
17
β˜… 101 β‘‚ 19 +1/day
Python
Osilly
Osilly
Interleaving-Reasoning-Generation

[ICLR 2026] This is an early exploration to introduce Interleaving Reasoning to Text-to-image Generation field and achieve the SoTA benchmark performance. It also significantly improves the quality, fine-grained details and aesthetic aspects of generated images.

Score
0
β˜… 100 β‘‚ 1 +1/day
Python
normal-computing
normal-computing
branches

Prototype advanced LLM algorithms for reasoning and planning.

Score
0
β˜… 98 β‘‚ 6 β€”
TypeScript
Related Topics
#llm#large-language-models#artificial-intelligence#ai#rag#chain-of-thought#knowledge-graph#deep-learning#chatgpt#prompt-engineering#rl#agentic-ai

Β© 2026 GitRepoTrend Β· GitHub repositories by topic Β· Updated weekly