Retrieval & Agents

ReAct

An agent pattern that interleaves reasoning and action in a loop: think, take an action with a tool, observe the result, repeat.

ReAct, short for reasoning and acting, structures an agent as a loop of thought, action, and observation. The model reasons about what it needs, takes an action such as calling a tool or searching, observes what comes back, and updates its plan, repeating until the task is done. This grounding in real feedback makes it far more reliable than reasoning in isolation, and it underlies many modern tool-using agents.