User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation

• URL: http://arxiv.org/abs/2604.03671v1
• Date: Sat, 04 Apr 2026 09:52:30 GMT
• Title: User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation
• Abstract summary: We propose a user simulator-guided multi-turn preference optimization conversational recommendation framework.<n>To align simulator-generated feedback with true user preferences in the absence of explicit labels, we enhance feedback quality via multi-task supervised fine-tuning.
• Score: 5.313432318455876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conversational Recommender Systems (CRSs) leverage natural language interactions for personalized recommendation, yet information-scarce dialogue histories and single-turn recommendation paradigms may severely hinder accurate modeling of complex user preferences. To alleviate this issue, recent studies have introduced LLM-based user simulators, which generate natural language feedback and perform simulated multi-turn interactions to assist recommendation. Nevertheless, since simulators cannot access true user preference labels during inference, their feedback may deviate from actual user interests, causing errors to accumulate over multiple interactions and severely affecting the generalization of the recommender. Inspired by the multi-step reasoning capabilities of LLMs and the effectiveness of reinforcement learning in policy optimization, we propose SMTPO, a user simulator-guided multi-turn preference optimization conversational recommendation framework. To align simulator-generated feedback with true user preferences in the absence of explicit labels, we enhance feedback quality via multi-task supervised fine-tuning (SFT), enabling the simulator to better reflect users' complex and diverse needs. To address the challenge of biased feedback destabilizing multi-turn optimization, we first allow the reasoning LLM-based recommender to learn preference reasoning and recommendation patterns through SFT and then employ reinforcement learning with fine-grained reward design to progressively align with true user preferences, improving recommendation performance. Extensive experiments on public datasets demonstrate the effectiveness and transferability of our method.

Related papers

• Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation [13.64805293826201]
  We propose a new approach that quantifies the effectiveness of each interaction by the reduction in the assistant's uncertainty, measured via entropy over recommendations.<n> Empirical results with supervised fine-tuning show that our method improves both recommendation quality and conversational efficiency.
  arXiv  Detail & Related papers  (2026-08-16T22:14:12Z)
• RecoWorld: Building Simulated Environments for Agentic Recommender Systems [55.979427290369216]
  We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems.<n>A user simulator reviews recommended items, updates its mindset, and when sensing potential user disengagement, generates reflective instructions.<n>The agentic recommender adapts its recommendations by incorporating these user instructions and reasoning traces, creating a dynamic feedback loop.
  arXiv  Detail & Related papers  (2025-09-12T16:44:34Z)
• Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User [117.82681846559909]
  Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations.<n>We propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs.
  arXiv  Detail & Related papers  (2025-04-29T06:37:30Z)
• Explainable Recommendation with Simulated Human Feedback [8.532115411106068]
  We propose a novel human-like feedback-driven optimization framework for explainable recommendations.<n>This framework employs a dynamic interactive optimization mechanism for achieving human-centered explainable requirements without incurring high labor costs.<n>In particular, we propose to utilize large language models (LLMs) as human simulators to predict human-like feedback for guiding the learning process.
  arXiv  Detail & Related papers  (2025-04-19T02:46:10Z)
• Reason4Rec: Large Language Models for Recommendation with Deliberative User Preference Alignment [69.11529841118671]
  We propose a new Deliberative Recommendation task, which incorporates explicit reasoning about user preferences as an additional alignment goal.<n>We then introduce the Reasoning-powered Recommender framework for deliberative user preference alignment.
  arXiv  Detail & Related papers  (2025-02-04T07:17:54Z)
• RosePO: Aligning LLM-based Recommenders with Human Values [38.029251417802044]
  We propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO) RosePO better aligns with customized human values during the post-training stage. Evaluation on three real-world datasets demonstrates the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-10-16T12:54:34Z)
• Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information [76.62949982303532]
  We propose a parameter-efficient Large Language Model Bi-Tuning framework for sequential recommendation with collaborative information (Laser) In our Laser, the prefix is utilized to incorporate user-item collaborative information and adapt the LLM to the recommendation task, while the suffix converts the output embeddings of the LLM from the language space to the recommendation space for the follow-up item recommendation. M-Former is a lightweight MoE-based querying transformer that uses a set of query experts to integrate diverse user-specific collaborative information encoded by frozen ID-based sequential recommender systems.
  arXiv  Detail & Related papers  (2024-09-03T04:55:03Z)
• A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems [14.646529557978512]
  Conversational Recommender System (CRS) leverages real-time feedback from users to dynamically model their preferences. Large Language Models (LLMs) has marked the onset of a new epoch in computational capabilities. We introduce a Controllable, scalable, and human-Involved (CSHI) simulator framework that manages the behavior of user simulators.
  arXiv  Detail & Related papers  (2024-05-13T03:02:56Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Reward Constrained Interactive Recommendation with Natural Language Feedback [158.8095688415973]
  We propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference. Our proposed framework is general and is further extended to the task of constrained text generation.
  arXiv  Detail & Related papers  (2020-05-04T16:23:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.