# Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User

arXiv: https://arxiv.org/abs/2504.20458 · HTML: https://mlsanity.com/paper/2504.20458/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems](https://mlsanity.com/paper/2002.09102/) (2020)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [Interactive Path Reasoning on Graph for Conversational Recommendation](https://mlsanity.com/paper/2007.00194/) (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)
- [CRSLab: An Open-Source Toolkit for Building Conversational Recommender System](https://mlsanity.com/paper/2101.00939/) (2021)
- [Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users](https://mlsanity.com/paper/2005.12979/) (2020)
- [Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information](https://mlsanity.com/paper/2112.08140/) (2021)
- [Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation](https://mlsanity.com/paper/2212.11868/) (2022)
- [TREA: Tree-Structure Reasoning Schema for Conversational Recommendation](https://mlsanity.com/paper/2307.10543/) (2023)
- [Improving Conversational Recommendation Systems via Counterfactual Data Simulation](https://mlsanity.com/paper/2306.02842/) (2023)
- [Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation](https://mlsanity.com/paper/2405.12119/) (2024)
- [Alleviating the Long-Tail Problem in Conversational Recommender Systems](https://mlsanity.com/paper/2307.11650/) (2023)

## Built on by (most cited first, 5 of 5)

- [Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptation](https://mlsanity.com/paper/2601.21797/) (2026)
- [LLM4Rail: An LLM-Augmented Railway Service Consulting Platform](https://mlsanity.com/paper/2507.23377/) (2025)
- [FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning](https://mlsanity.com/paper/2603.11901/) (2026)
- [Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search](https://mlsanity.com/paper/2609.00618/) (2026)
- [RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce](https://mlsanity.com/paper/2609.38974/) (2026)

## Abstract (arXiv)

Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations. A fundamental challenge in CRSs lies in effectively understanding user preferences from conversations. User preferences can be multifaceted and complex, posing significant challenges for accurate recommendations even with access to abundant external knowledge. While interaction with users can clarify their true preferences, frequent user involvement can lead to a degraded user experience. To address this problem, we propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs. The simulated user provides feedback to the items recommended by CRSs, enabling them to better capture intricate user preferences through multi-turn interaction. Inspired by generative reward models, we design two types of feedback actions for the simulated user: i.e., generative item scoring, which offers coarse-grained feedback, and attribute-based item critique, which provides fine-grained feedback. To ensure seamless integration, these feedback actions are unified into an instruction-based format, allowing the development of a unified simulated user via instruction tuning on synthesized data. With this simulated user, automatic multi-turn interaction with CRSs can be effectively conducted. Furthermore, to strike a balance between effectiveness and efficiency, we draw inspiration from the paradigm of reward-guided search in complex reasoning tasks and employ beam search for the interaction process. On top of this, we propose an efficient candidate ranking method to improve the recommendation results derived from interaction. Extensive experiments on public datasets demonstrate the effectiveness, efficiency, and transferability of our approach.