Retrieval-Augmented Reasoning
An advanced approach where an AI model interleaves retrieval with reasoning steps, fetching new information mid-reasoning rather than retrieving everything upfront.
Why It Matters
RAR handles complex multi-step questions that require gathering different information at each reasoning step — far beyond what single-retrieval RAG can handle.
Example
Answering 'Which company in our portfolio had the highest revenue growth and what was their main product?' by first retrieving portfolio data, then revenue data for each company, then product data for the top performer.
Think of it like...
Like a detective who follows each clue to the next — gathering evidence step by step as the investigation unfolds, rather than requesting all possible files upfront.
Related Terms
Retrieval-Augmented Generation
A technique that enhances LLM outputs by first retrieving relevant information from external knowledge sources and then using that information as context for generation. RAG combines the power of search with the fluency of language models.
Reasoning
An AI model's ability to think logically, make inferences, draw conclusions, and solve problems that require multi-step thought. Reasoning goes beyond pattern matching to genuine logical analysis.
Chain-of-Thought
A prompting technique where the model is encouraged to show its step-by-step reasoning process before arriving at a final answer. This improves accuracy on complex reasoning tasks.
Agentic RAG
An advanced RAG pattern where an AI agent dynamically decides what to retrieve, how to refine queries, and when to search again based on the quality of initial results.
Planning
An AI agent's ability to break down complex goals into a sequence of steps and determine the best order of actions to accomplish a task. Planning involves reasoning about dependencies, priorities, and contingencies.