# Leveraging Memory Retrieval to Enhance LLM-based Generative Recommendation

arXiv: https://arxiv.org/abs/2412.17593 · HTML: https://mlsanity.com/paper/2412.17593/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2024.

## Built on by (most cited first, 6 of 6)

- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [SteerX: Disentangled Steering for LLM Personalization](https://mlsanity.com/paper/2510.22256/) (2025)
- [PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models](https://mlsanity.com/paper/2601.10532/) (2026)
- [Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents](https://mlsanity.com/paper/2601.06490/) (2026)
- [Self-Evolving Memory for Generative Recommendation](https://mlsanity.com/paper/2609.15598/) (2026)

## Abstract (arXiv)

Leveraging Large Language Models (LLMs) to harness user-item interaction histories for item generation has emerged as a promising paradigm in generative recommendation. However, the limited context window of LLMs often restricts them to focusing on recent user interactions only, leading to the neglect of long-term interests involved in the longer histories. To address this challenge, we propose a novel Automatic Memory-Retrieval framework (AutoMR), which is capable of storing long-term interests in the memory and extracting relevant information from it for next-item generation within LLMs. Extensive experimental results on two real-world datasets demonstrate the effectiveness of our proposed AutoMR framework in utilizing long-term interests for generative recommendation.