Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation

2026-03-19

AI Summary

This work addresses the limitation of existing conversational recommender systems, which heavily rely on large-scale real-world dialogue data, while traditional simulation methods often produce scripted and unnatural conversations. To overcome this, the paper proposes a novel two-agent interactive dialogue simulation framework that operates without predefined target items. In this framework, two independent large language models autonomously assume the roles of user and recommender, engaging in real-time interaction grounded in a user preference profile and target attributes to generate high-quality dialogues. This approach represents the first end-to-end dialogue simulation method that requires no reference item, significantly outperforming existing techniques in both dialogue naturalness and diversity. Its effectiveness and scalability are rigorously validated through quantitative metrics and human evaluation.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Training conversational recommender systems (CRS) requires extensive dialogue data, which is challenging to collect at scale. To address this, researchers have used simulated user-recommender conversations. Traditional simulation approaches often utilize a single large language model (LLM) that generates entire conversations with prior knowledge of the target items, leading to scripted and artificial dialogues. We propose a reference-free simulation framework that trains two independent LLMs, one as the user and one as the conversational recommender. These models interact in real-time without access to predetermined target items, but preference summaries and target attributes, enabling the recommender to genuinely infer user preferences through dialogue. This approach produces more realistic and diverse conversations that closely mirror authentic human-AI interactions. Our reference-free simulators match or exceed existing methods in quality, while offering a scalable solution for generating high-quality conversational recommendation data without constraining conversations to pre-defined target items. We conduct both quantitative and human evaluations to confirm the effectiveness of our reference-free approach.

Problem

• conversational recommender systems
• dialogue simulation
• reference-free
• large language models
• user-recommender interaction

Innovation

• reference-free simulation
• conversational recommender systems
• independent LLMs
• real-time interaction
• preference inference