How do agents plan and reason?

LangChain agents use the ReAct (Reasoning + Acting) framework to plan and reason. The model is prompted to produce interleaved Thought, Action, and Observation sequences. The Thought is the model's explicit reasoning about what to do next; the Action is the tool call decision; the Observation is the tool's returned result. This cycle repeats until the model produces a "Final Answer".

A ReAct trace looks like this:

Question: Who is the CEO of Anthropic and when was the company founded?

Thought: I need to search for information about Anthropic.
Action: search
Action Input: "Anthropic CEO founder"
Observation: Anthropic was founded in 2021. Dario Amodei is the CEO.

Thought: I now have both pieces of information needed to answer.
Final Answer: Anthropic's CEO is Dario Amodei. The company was founded in 2021.

For models with native function calling (OpenAI, Anthropic), the reasoning is more structured: the model returns a JSON tool call object rather than parsing free text, which is more reliable. The OpenAI Tools Agent uses this approach. Newer techniques like chain-of-thought prompting and tree-of-thought can be integrated to improve multi-step reasoning quality by providing examples of good reasoning chains in the system prompt.

Invest now in Acorns!!! 🚀
Join Acorns and get your $5 bonus!

Acorns is a micro-investing app that automatically invests your "spare change" from daily purchases into diversified, expert-built portfolios of ETFs. It is designed for beginners, allowing you to start investing with as little as $5. The service automates saving and investing. Disclosure: I may receive a referral bonus.

Invest now!!! Get Free equity stock (US, UK only)!

Use Robinhood app to invest in stocks. It is safe and secure. Use the Referral link to claim your free stock when you sign up!.

The Robinhood app makes it easy to trade stocks, crypto and more.

Webull! Receive free stock by signing up using the link: Webull signup.