This article describes the four main approaches to building reasoning models, or how we can enhance LLMs with reasoning capabilities. I hope this provides valuable insights and helps you navigate the rapidly evolving literature and hype surrounding this topic.
In 2024, the LLM field saw increasing specialization. Beyond pre-training and fine-tuning, we witnessed the rise of specialized applications, from RAGs to code assistants. I expect this trend to accelerate in 2025, with an even greater emphasis on domain- and application-specific optimizations (i.e., "specializations").
Variants of Deepseek R1 models:
magazine.sebastianraschka.com
In 2024, the LLM field saw increasing specialization. Beyond pre-training and fine-tuning, we witnessed the rise of specialized applications, from RAGs to code assistants. I expect this trend to accelerate in 2025, with an even greater emphasis on domain- and application-specific optimizations (i.e., "specializations").
Variants of Deepseek R1 models:
Understanding Reasoning LLMs
Methods and Strategies for Building and Refining Reasoning Models
magazine.sebastianraschka.com