reasoning
Tracked open-source repos tagged reasoning, sorted by stars.
- #31★ 1,245+2Star change over the last 7 days
- #32★ 1,137+3Star change over the last 7 days
- #33★ 1,121+1Star change over the last 7 days
- #34★ 1,090+11Star change over the last 7 days
- #35
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
★ 1,025+2Star change over the last 7 days - #36
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
★ 1,015+0Star change over the last 7 days - #37
[ACL 2023] Reasoning with Language Model Prompting: A Survey
★ 1,007+1Star change over the last 7 days - #38
Pretraining and inference code for a large-scale depth-recurrent language model
★ 942+22Star change over the last 7 days - #39★ 928+4Star change over the last 7 days
- #40
[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources
★ 861+6Star change over the last 7 days - #41
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
★ 820+0Star change over the last 7 days - #42★ 769+1Star change over the last 7 days
- #43★ 741+6Star change over the last 7 days
- #44★ 671+10Star change over the last 7 days
- #45
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
★ 669-1Star change over the last 7 days - #46
PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning
★ 657+5Star change over the last 7 days - #47
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models
★ 657+0Star change over the last 7 days - #48
Latest Advances on Long Chain-of-Thought Reasoning
★ 647-1Star change over the last 7 days - #49
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
★ 642+2Star change over the last 7 days - #50
Explore the Multimodal “Aha Moment” on 2B Model
★ 623+0Star change over the last 7 days - #51
code and docs for the EMNLP paper "DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning"
★ 562+0Star change over the last 7 days - #52★ 552-1Star change over the last 7 days
- #53
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"
★ 532-1Star change over the last 7 days - #54★ 518+2Star change over the last 7 days
- #55
🔥🔥🔥[AAAI 2026 Oral] Official Implementation of Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
★ 511+0Star change over the last 7 days - #56
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
★ 501—Star change over the last 7 days
