AI / Agentic AI Interview Questions
Define the ReAct framework?
ReAct, short for Reasoning and Acting, is an agent pattern that interleaves explicit reasoning steps with tool-based actions, rather than jumping straight from input to action.
Loop: Thought = LM(context, previous_observation) Action = Parse(Thought) Observation = Execute(Action) context += [Thought, Action, Observation]
At each step, the agent writes out a thought about what to do next, takes an action based on that thought, observes the result, and folds that observation back into its context before deciding the next step.
Because the reasoning is explicit, ReAct agents can recover from errors mid-task, if a tool call fails, the agent can reason about the failure and try a different approach instead of silently continuing down a broken path.
What does ReAct interleave at every step?
What lets a ReAct agent recover from a failed tool call?
More Related questions...
