Awesome-Reasoning-Foundation-Models

Why we included this project

Anyone trying to get a handle on how large language and multimodal models reason will find this list a useful shortcut. It groups foundation models by modality, then sorts reasoning work into categories like commonsense, mathematical, logical, causal, visual, audio, multimodal, and agent reasoning, with a separate section covering techniques such as pre-training, fine-tuning, alignment, mixture-of-experts, in-context learning, and autonomous agents. The companion survey paper explains the big picture, while the list itself links to the specific papers and benchmarks behind each claim. That makes it handy for teams scoping a reasoning project or students assembling a literature review, especially for seeing which benchmarks keep showing up for a given capability. It is a research map to read, not software to deploy.