Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning

Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often requires abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-ZERO, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-ZERO prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-ZERO on the goal-oriented task Persua-sionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than Chat-GPT during interactive evaluations 1 .