Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates

• URL: http://arxiv.org/abs/2510.20260v1
• Date: Thu, 23 Oct 2025 06:31:00 GMT
• Title: Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates
• Authors: Changping Meng, Hongyi Ling, Jianling Wang, Yifan Liu, Shuzhou Zhang, Dapeng Hong, Mingyan Gao, Onkar Dalal, Ed Chi, Lichan Hong, Haokai Lu, Ningren Han,
• Abstract summary: Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities.<n>This paper investigates strategies for updating LLM-powered recommenders, focusing on the trade-offs between ongoing fine-tuning and Retrieval-Augmented Generation (RAG)<n>We propose a hybrid update strategy that leverages the long-term knowledge adaptation of periodic fine-tuning with the agility of low-cost RAG.
• Score: 11.974496007403694
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content poses a significant challenge: While initial fine-tuning aligns LLMs with domain knowledge and user preferences, it fails to capture such real-time changes, necessitating robust update mechanisms. This paper investigates strategies for updating LLM-powered recommenders, focusing on the trade-offs between ongoing fine-tuning and Retrieval-Augmented Generation (RAG). Using an LLM-powered user interest exploration system as a case study, we perform a comparative analysis of these methods across dimensions like cost, agility, and knowledge incorporation. We propose a hybrid update strategy that leverages the long-term knowledge adaptation of periodic fine-tuning with the agility of low-cost RAG. We demonstrate through live A/B experiments on a billion-user platform that this hybrid approach yields statistically significant improvements in user satisfaction, offering a practical and cost-effective framework for maintaining high-quality LLM-powered recommender systems.

Related papers

• Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation [56.92367609590823]
  Long Chain-of-Thought (Long CoT) reasoning has shown promise in Large Language Models (LLMs)<n>We argue that Long CoT is inherently ill-suited for the sequential recommendation domain.<n>We propose RISER, a novel Reinforced Item Space Exploration framework for Recommendation.
  arXiv  Detail & Related papers  (2026-01-31T10:02:43Z)
• LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation [3.247395557141079]
  We propose LLM-Enhanced Reinforcement Learning (LERL), a novel hierarchical recommendation framework.<n>LERL consists of a high-level LLM-based planner that selects semantically diverse content categories, and a low-level RL policy that recommends personalized items.<n>LERL significantly improves long-term user satisfaction when compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-01-27T13:22:30Z)
• Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts [63.412646471177645]
  We propose a novel Reinforced Strategy Optimization (RSO) method for Conversational Recommender Systems (CRSs)<n>RSO decomposes the process of generating strategy-driven response decisions into the macro-level strategy planning and micro-level strategy adaptation.<n>Experiments show that RSO significantly improves interaction performance compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-09-30T11:12:01Z)
• What LLMs Miss in Recommendations: Bridging the Gap with Retrieval-Augmented Collaborative Signals [4.297070083645049]
  User-item interactions contain rich collaborative signals that form the backbone of many successful recommender systems.<n>It remains unclear whether large language models (LLMs) can effectively reason over this type of collaborative information.<n>We introduce a simple retrieval-augmented generation (RAG) method that enhances LLMs by grounding their predictions in structured interaction data.
  arXiv  Detail & Related papers  (2025-05-27T05:18:57Z)
• DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation [83.21140655248624]
  Large language models (LLMs) have been introduced into recommender systems (RSs)<n>We propose DeepRec, a novel LLM-based RS that enables autonomous multi-turn interactions between LLMs and TRMs for deep exploration of the item space.<n> Experiments on public datasets demonstrate that DeepRec significantly outperforms both traditional and LLM-based baselines.
  arXiv  Detail & Related papers  (2025-05-22T15:49:38Z)
• Large Language Model driven Policy Exploration for Recommender Systems [50.70228564385797]
  offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments.<n>Online RL-based RS also face challenges in production deployment due to the risks of exposing users to untrained or unstable policies.<n>Large Language Models (LLMs) offer a promising solution to mimic user objectives and preferences for pre-training policies offline.<n>We propose an Interaction-Augmented Learned Policy (iALP) that utilizes user preferences distilled from an LLM.
  arXiv  Detail & Related papers  (2025-01-23T16:37:44Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.<n>We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• Large Language Model as a Catalyst: A Paradigm Shift in Base Station Siting Optimization [62.16747639440893]
  Large language models (LLMs) and their associated technologies advance, particularly in the realms of prompt engineering and agent engineering.<n>Our proposed framework incorporates retrieval-augmented generation (RAG) to enhance the system's ability to acquire domain-specific knowledge and generate solutions.
  arXiv  Detail & Related papers  (2024-08-07T08:43:32Z)
• LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation [52.55639178180821]
  The study on multi-scenario recommendation (MSR) has attracted much attention, which uses the data from all scenarios to simultaneously improve their recommendation performance.<n>Existing methods tend to integrate insufficient scenario knowledge and neglect learning personalized cross-scenario preferences, thus leading to sub-optimal performance.<n>We propose a large language model (LLM)-enhanced paradigm LLM4MSR to fill these gaps.
  arXiv  Detail & Related papers  (2024-06-18T11:59:36Z)
• Efficient and Responsible Adaptation of Large Language Models for Robust Top-k Recommendations [11.004673022505566]
  Long user queries from millions of users can degrade the performance of large language models for recommendation. We propose a hybrid task allocation framework that utilizes the capabilities of both large language models and traditional recommendation systems. Our results on three real-world datasets show a significant reduction in weak users and improved robustness of RSs to sub-populations.
  arXiv  Detail & Related papers  (2024-05-01T19:11:47Z)
• Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena [25.865825113847404]
  We introduce AucArena, a novel evaluation suite that simulates auctions. We conduct controlled experiments using state-of-the-art Large Language Models (LLMs) to power bidding agents to benchmark their planning and execution skills.
  arXiv  Detail & Related papers  (2023-10-09T14:22:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.