passdrill
AI & LLM Engineering · AI Agents & Tool Use · Card 015/022 medium

A puzzle-solving agent using the ReAct pattern commits to one Thought, takes one Action, reads the Observation, and moves forward to its next Thought in a single unbroken line -- it never goes back to reconsider an earlier step once it has moved on. For puzzles where an early move can look reasonable but turns out to be a dead end many steps later, a different framework instead generates several candidate 'thoughts' at each step, evaluates how promising each one looks, and uses a search procedure such as breadth-first or depth-first search to explore multiple branches and backtrack away from ones that stop looking promising. What is the defining difference this second framework introduces compared to ReAct's approach?

  1. It removes the need for the model to produce any intermediate reasoning text at all, replacing thoughts entirely with a single numeric score per step
  2. It requires every branch explored to be executed as a real action against an external tool before it can be evaluated, unlike ReAct which never calls any tools
  3. It guarantees that the globally best solution will always be found on the first attempt, regardless of how the evaluation heuristic scores each candidate thought
  4. It reframes problem solving as a search over a tree of intermediate reasoning steps, generating multiple candidate thoughts at a branching point, evaluating their promise heuristically, and backtracking away from weak branches, instead of committing irreversibly to one linear Thought/Action/Observation sequence the way ReAct does
Next card → Shuffle