ReAct Framework

ReAct (Reasoning + Acting) is a prompting paradigm and behavioral framework for llm-based agents. Unlike standard Chatbots that only generate text, ReAct enables agents to reason through complex tasks by interleaving thought processes with external actions.

Core Mechanism

The framework operates on a loop of three steps:

  1. Thought: The model reasons about the current state and decides on a next action.
  2. Action: The model executes an operation (e.g., calling an application-programming-interface-api, searching a knowledge-base).
  3. Observation: The model processes the output of the action, feeding it back into the reasoning loop.

This iterative cycle allows agents to handle multi-step problems, verify information, and adapt to dynamic environments.

Integration & Context

References

AI Agents Explained: ReAct Framework, Behavioral Types, and Google ADK