GenRec: An LLM-Backed Recommendation Ranker at Netflix

Netflix researchers introduced GenRec, an LLM-backed recommendation ranker built on an in-house foundational LLM, in a paper submitted to arXiv on Aug 10, 2026. In a large-scale A/B test, GenRec achieved statistically significant gains in offline and online metrics over the current production ranker while using substantially fewer Phase-2 labeled training examples and input signals. The two-phase framework adapts an open-source LLM to Netflix data, then post-trains it with recommendation-ranking data and reward signals to align with business requirements and long-term member satisfaction.

Computer Science Information Retrieval Submitted on 10 Aug 2026 v1 https://arxiv.org/abs/2608.10257v1 , last revised 21 Aug 2026 this version, v2 Title:GenRec: An LLM-Backed Recommendation Ranker at Netflix View PDF /pdf/2608.10257 HTML experimental https://arxiv.org/html/2608.10257v2 Abstract:Large language models LLMs are reshaping recommender systems by enabling richer modeling of users, content, and context directly in natural language. At Netflix, we are exploring this direction through GenRec, an LLM-backed recommendation ranker built on top of an in-house foundational LLM. GenRec follows a two-phase framework: Phase 1 adapts an open-source LLM to Netflix data, developing deep understanding of the catalog and member behavior while balancing capabilities such as content understanding and instruction following. Phase 2 post-trains this foundation model with recommendation-ranking specific data, labels, and reward signals, aiming to align the ranker with business requirements and long-term member satisfaction. This paper focuses on Phase 2 and the transition from a traditional discriminative ranker with thousands of engineered features to an LLM-backed ranker driven by verbalized user histories and context. We describe our design for input verbalization and context engineering, post-training data construction, reward integration, model architecture, and a cost-constrained serving design based on a prefill-only inference approach. We report results from a large-scale A/B test comparing GenRec against the current production ranker model, where we show that a GenRec model trained with substantially fewer Phase-2 labeled training examples and input signals can achieve statistically significant gains in offline and online metrics. We discuss how LLM-backed recommenders could shift the recommendation paradigm: from feature engineering to context engineering, and from bespoke architectures to shared foundation backbones. We also outline practical lessons for serving such systems under real-world resource constraints. Submission history From: Ying Li view email /show-email/a7a5002e/2608.10257 Mon, 10 Aug 2026 21:43:14 UTC 2,134 KB v1 /abs/2608.10257v1 v2 Fri, 21 Aug 2026 22:32:55 UTC 2,134 KB Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .