# Large Language Model Simulator for Cold-Start Recommendation

arXiv: https://arxiv.org/abs/2402.09176 · HTML: https://mlsanity.com/paper/2402.09176/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2024.

## Built on by (most cited first, 10 of 10)

- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions](https://mlsanity.com/paper/2503.09311/) (2025)
- [IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu](https://mlsanity.com/paper/2603.01590/) (2026)
- [Distilling Large Language Models for Network Active Queue Management](https://mlsanity.com/paper/2501.16734/) (2025)
- [Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning](https://mlsanity.com/paper/2511.05494/) (2025)
- [Awakening Dormant Users: Generative Recommendation with Counterfactual Functional Role Reasoning](https://mlsanity.com/paper/2602.13134/) (2026)
- [Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search](https://mlsanity.com/paper/2605.17994/) (2026)
- [Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations](https://mlsanity.com/paper/2606.06779/) (2026)

## Abstract (arXiv)

Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely solely on content features, limiting their recommendation performance and impacting user experience and revenue. Current models generate synthetic behavioral embeddings from content features but fail to address the core issue: the absence of historical behavior data. To tackle this, we introduce the LLM Simulator framework, which leverages large language models to simulate user interactions for cold items, fundamentally addressing the cold-start problem. However, simply using LLM to traverse all users can introduce significant complexity in billion-scale systems. To manage the computational complexity, we propose a coupled funnel ColdLLM framework for online recommendation. ColdLLM efficiently reduces the number of candidate users from billions to hundreds using a trained coupled filter, allowing the LLM to operate efficiently and effectively on the filtered set. Extensive experiments show that ColdLLM significantly surpasses baselines in cold-start recommendations, including Recall and NDCG metrics. A two-week A/B test also validates that ColdLLM can effectively increase the cold-start period GMV.