SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search

Conversational Recommender Systems (CRS) proactively engage users in interactive dialogues to elicit user preferences and provide personalized recommendations. Existing methods train Reinforcement Learning (RL)-based agent with greedy action selection or sampling strategy, and may suffer from suboptimal conversational planning. To address this, we present a novel Monte Carlo Tree Search (MCTS)-based CRS framework, Strategic Action Planning with Intelligent Exploration and Non-myopic Tactics, referred to as SAPIENT. SAPIENT consists of a conversational agent (S-agent) and a conversational planner (S-planner). S-planner builds a conversational search tree with MCTS based on the initial actions proposed by S-agent to find conversation plans. The best conversation plans from S-planner are used to guide the training of S-agent, creating a self-training loop where S-agent can iteratively refine its capacity for conversational planning. Furthermore, we propose an efficient alternative SAPIENT-e for trade-off between training efficiency and performance. Extensive experiments on four benchmark datasets validate the effectiveness of our approach, showing that SAPIENT outperforms the state-of-the-art baselines. Our anonymous code and data are accessible through https://anonymous.4open.science/r/SAPIENT/.