Multi-step reasoning
Multi-step reasoning is a reasoning approach in which an LLM arrives at a final answer not through a single response generation, but by going through multiple intermediate steps, such as generating sub-questions, verifying partial answers, and retrieving additional information.
## Limitations of Simple Question Answering A factual lookup such as "What is the revenue?" can be completed in a single step. However, a question like "What initiatives did the person in charge of the division with the highest year-over-year revenue growth introduce?" cannot be answered without going through multiple intermediate steps: comparing sales data → identifying the division → identifying the person in charge → searching for information on the initiatives. Multi-step reasoning refers to an approach in which an LLM internally decomposes such complex questions and solves them incrementally. It is an extension of Chain-of-Thought (CoT) prompting, but differs in that, when combined with RAG, a search of external data sources is inserted at each step. ## Relationship with Agentic RAG Agentic RAG can be understood as an implementation of multi-step reasoning as an agent loop. The agent determines "what should be investigated next" and cycles through search → evaluation → re-search. Multi-step reasoning is the design pattern for that thought process, while Agentic RAG is the architecture that executes it. ## Accuracy vs. Speed Trade-off The more steps involved, the greater the comprehensiveness of the answer; however, the LLM inference cost and search latency accumulate at each step. In practice, many systems are designed with an upper limit on the number of steps (typically 3–5) and an early termination mechanism that triggers once sufficient information has been gathered.
Related Terms
LLM (Large Language Model)
LLM (Large Language Model) is a general term for neural network models pre-trained on massive amounts of text data, containing billions to trillions of parameters, capable of understanding and generating natural language with high accuracy.
Local LLM
A local LLM refers to an operational model in which a large language model is run directly on one's own server or PC, without going through a cloud API.
Agentic RAG
Agentic RAG is an architecture in which an LLM autonomously and iteratively generates search queries, evaluates results, and decides whether to re-retrieve information as an agent, achieving answer accuracy that cannot be obtained with simple single-turn RAG.
