# LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations

arXiv: https://arxiv.org/abs/2404.00702 · HTML: https://mlsanity.com/paper/2404.00702/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2024.

## Built on by (most cited first, 13 of 13)

- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning](https://mlsanity.com/paper/2505.14069/) (2025)
- [LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation](https://mlsanity.com/paper/2405.20646/) (2024)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models](https://mlsanity.com/paper/2507.06507/) (2025)
- [IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu](https://mlsanity.com/paper/2603.01590/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks](https://mlsanity.com/paper/2604.12096/) (2026)
- [A Language-Driven Framework for Improving Personalized Recommendations: Merging LLMs with Traditional Algorithms](https://mlsanity.com/paper/2507.07251/) (2025)
- [Membership Inference Attacks on In-Context Examples in LLM-based Recommender Systems](https://mlsanity.com/paper/2508.18665/) (2025)
- [Trie-Aware Transformers for Generative Recommendation](https://mlsanity.com/paper/2602.21677/) (2026)
- [Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search](https://mlsanity.com/paper/2605.17994/) (2026)

## Abstract (arXiv)

The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations. To address this problem, Large Language Models (LLMs) can model recommendation tasks as language analysis tasks and provide zero-shot results based on their vast open-world knowledge. However, the large scale of the item corpus poses a challenge to LLMs, leading to substantial token consumption that makes it impractical to deploy in real-world recommendation systems. To tackle this challenge, we introduce a tree-based LLM recommendation framework LLMTreeRec, which structures all items into an item tree to improve the efficiency of LLM's item retrieval. LLMTreeRec achieves state-of-the-art performance under the system cold-start setting in two widely used datasets, which is even competitive with conventional deep recommendation systems that use substantial training data. Furthermore, LLMTreeRec outperforms the baseline model in A/B testing on Huawei industrial systems. Consequently, LLMTreeRec demonstrates its effectiveness as an industry-friendly solution that has been successfully deployed online. Our code is available at: https://github.com/Applied-Machine-Learning-Lab/LLMTreeRec.