passdrill
AI & LLM Engineering · Prompt Engineering · Card 025/027 medium

An engineer is building an agent that must look up information from a search API partway through solving a multi-step question and adjust its plan based on what the search returns. According to Yao et al. (2022), "ReAct: Synergizing Reasoning and Acting in Language Models," what does the ReAct prompting framework do to make this possible?

  1. Generating only the sequence of actions to take, such as API calls, without ever producing any intermediate natural-language reasoning
  2. Interleaving natural-language reasoning traces with task-specific actions and the observations those actions return, within a single prompted trajectory, so reasoning can decide the next action and each new observation can update the reasoning that follows
  3. Training a separate reasoning model and a separate acting model with reinforcement learning and combining their outputs after each has finished running independently
  4. Producing a chain-of-thought explanation for a problem but never issuing any call to an external tool or API
Next card → Shuffle