Social category
Thinking
How one mind reasons — loops, planning, self-critique, search, code-as-action.
ReAct
Think, act, look, think again.
The agent alternates iteratively between a reasoning step and a tool call until the goal is achieved. It observes the result of the action and derives the next step from it.
Trade-off High adaptability is gained at the expense of a significantly higher token and call volume per step.
Plan-and-Execute
Plan once. Execute the list.
An agent first generates a complete plan and then executes the steps sequentially or in a controlled manner.
Trade-off Better structure and testability compared to ReAct, but carries the risk of the agent clinging to outdated or unsuitable plans.
ReWOO
Plan. Batch. Fold.
The agent plans all necessary tool calls upfront, executes them in batch, and uses the aggregated results for the final answer.
Trade-off Significantly lower LLM costs and latency, but at the expense of adaptability during execution.
Reflexion
Act. Evaluate. Reflect. Retry.
The agent critically evaluates its own intermediate results and uses this feedback to improve the next steps or output in iterative loops.
Trade-off Leads to higher result quality, but incurs additional token costs and can lead to false confidence.
Tree of Thoughts
Branch the reasoning. Keep the best leaf.
The agent explores multiple reasoning paths simultaneously like a tree diagram and selects promising paths to pursue while discarding dead ends.
Trade-off Enables a much broader and deeper exploration of the solution space, but leads to exponentially increasing computational and token overhead.
Self-Consistency
Vote across many minds. Settle on the majority.
The system generates multiple independent reasoning outputs for the same prompt, and then merges the results via consensus or voting for a final answer.
Trade-off Significantly more robust answers against false paths, paid for by multiple inference costs.
CodeAct
Think in code. Execute. Observe. Repeat.
The agent uses executable code rather than pure text as its primary medium for action and reasoning — it writes code, runs it in a sandbox, observes the typed result, and iterates, so a computation is executed rather than approximated in prose.
Trade-off Maximum precision and reproducibility oppose a high sandbox, security, and runtime overhead.
Where to next