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

arXiv: https://arxiv.org/abs/2604.03671 · HTML: https://mlsanity.com/paper/2604.03671/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks](https://mlsanity.com/paper/2504.05118/) (2025)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models](https://mlsanity.com/paper/2305.13112/) (2023)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- [Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation](https://mlsanity.com/paper/2502.02061/) (2025)
- [Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation](https://mlsanity.com/paper/2506.05069/) (2025)
- [Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models](https://mlsanity.com/paper/2403.12388/) (2024)
- [TREA: Tree-Structure Reasoning Schema for Conversational Recommendation](https://mlsanity.com/paper/2307.10543/) (2023)
- [Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent](https://mlsanity.com/paper/2506.14302/) (2025)

## Built on by (most cited first, 1 of 1)

- [Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders](https://mlsanity.com/paper/2610.17771/) (2026)

## Abstract (arXiv)

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.