# Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework

arXiv: https://arxiv.org/abs/2607.00010 · HTML: https://mlsanity.com/paper/2607.00010/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 26 of 26)

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [HYDRA: Model Factorization Framework for Black-Box LLM Personalization](https://mlsanity.com/paper/2406.02888/) (2024)
- [The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective](https://mlsanity.com/paper/2312.15524/) (2023)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- [Evaluating Conversational Recommender Systems via User Simulation](https://mlsanity.com/paper/2006.08732/) (2020)
- [Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems](https://mlsanity.com/paper/2105.03748/) (2021)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [USimAgent: Large Language Models for Simulating Search Users](https://mlsanity.com/paper/2403.09142/) (2024)
- [How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.16416/) (2024)
- [DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues](https://mlsanity.com/paper/2405.13028/) (2024)
- [PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning](https://mlsanity.com/paper/2402.17188/) (2024)
- [A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems](https://mlsanity.com/paper/2405.08035/) (2024)
- [RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems](https://mlsanity.com/paper/2507.22897/) (2025)
- [RecDCL: Dual Contrastive Learning for Recommendation](https://mlsanity.com/paper/2401.15635/) (2024)
- [D2K: Turning Historical Data into Retrievable Knowledge for Recommender Systems](https://mlsanity.com/paper/2401.11478/) (2024)

## Abstract (arXiv)

Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time. However, there are two key obstacles in the CRS domain: evaluation and access to training data. Evaluating CRSs through real human studies is more critical than for traditional recommender systems, yet such studies are both costly and time-consuming. Moreover, CRS interaction data are often difficult to obtain for model training due to privacy concerns. Large language model (LLM)-based user simulators have shown promise in addressing both challenges by generating synthetic user interactions for evaluation and training. However, existing approaches suffer from systematic positive bias, data leakage, and limited behavioral diversity, and they rely on brittle manual prompt engineering that requires extensive domain expertise. In this paper, we propose a framework to automatically optimize prompts for LLM-based user simulators in CRSs, simultaneously mitigating these issues. Experimental results demonstrate that the proposed framework achieves improved behavioral alignment with human interaction patterns compared to baseline methods across diverse prompt settings.