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

TL;DR

SAPIENT introduces a Monte Carlo Tree Search-based framework for conversational recommendation systems, enabling strategic planning and iterative self-improvement to outperform existing methods.

Contribution

The paper proposes a novel MCTS-based framework with a self-training loop for improved conversational planning in CRS, addressing suboptimal strategies of prior RL-based methods.

Findings

Outperforms state-of-the-art baselines on four benchmark datasets.

Demonstrates effective strategic planning in multi-turn conversations.

Balances training efficiency and performance with an efficient variant.

Abstract

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 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 improve its capability for conversational planning. Furthermore, we propose an efficient variant SAPIENT 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 code and data are accessible through https://github.com/ninglab/SAPIENT.