microsoft/rStar

math reasoning model using agentic RL, efficient tool use, strong benchmark results

AI model for solving complex reasoning tasks with efficient architecture
sapientinc/HRM
tools for building and evaluating advanced LLM reasoning algorithms
maitrix-org/llm-reasoners
open-source large language model for reasoning, coding, and agents
zai-org/GLM-4.5
Step-by-step code for adding reasoning to a pre-trained LLM, with hands-on examples and explanations
rasbt/reasoning-from-scratch
open-source large language model focused on complex reasoning
MetaStone-AI/XBai-o4
Tool for building and optimizing prompt programs for large language models
microsoft/sammo
post-training recipe using RL to boost reasoning in language models
ChenxinAn-fdu/POLARIS
open-source reinforcement learning for language models
agentica-project/rllm
Open-source toolkit for agentic retrieval, research, and question answering over docs and web
SciPhi-AI/R2R
Microsoft’s open-source foundation model for multimodal AI agents
microsoft/Magma