Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning

[2607.14192] Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2607.14192 (cs) [Submitted on 15 Jul 2026 ( v1 ), last revised 21 Aug 2026 (this version, v3)] Title: Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning Authors: Dingsu Wang , Filip Ryzner , Kelly He , Armando Ordorica , David Woo , Aditya Mantha , Liyao Lu , Usha Amrutha Nookala , Haoran Guo , Jiacong He , Olafur Gudmundsson , Matt Chun , Krystal Benitez , Haibin Xie , Alekhya Pyla , Sameer Jain , Zhongjian Jiang , Shruthi Hariharan , Dhruvil Deven Badani , Yijie Dylan Wang View PDF HTML (experimental) Abstract: As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral signals to a broader emphasis on long-term user engagement and retention. However, directly optimizing retention is difficult because return signals are sparse, delayed, and only partially attributable to earlier recommendations. Prior work has addressed this challenge with sequential modeling and reinforcement learning, but these approaches typically require task specific reward engineering, substantial computational overhead, and surface specific implementations that are difficult to generalize. In this paper, we present a unified, model-agnostic downstream reward framework for optimizing long-term user value in large-scale recommendation systems. First, we formulate the downstream reward learning problem and develop an offline screening framework to identify session level behaviors that are both observable early and predictive of future retention. We then propose several model-agnostic downstream rewards signals derived from observed user action patterns across multiple sources. We further discuss the engineering effort to productionize the proposed rewards derivations and challenges we faced when adding them to our ranking models. Online A/B experiments demonstrate consistent improvements in engagement and retention-related metrics, and the framework has been deployed across multiple Pinterest surfaces, including Homefeed, Related Pins, Search, and Notifications. Comments: Recsys 2026, revised version Subjects: Machine Learning (cs.LG) ; Information Retrieval (cs.IR) Cite as: arXiv:2607.14192 [cs.LG] (or arXiv:2607.14192v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2607.14192 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1145/3773078.3831912 Focus to learn more DOI(s) linking to related resources Submission history From: Dingsu Wang [ view email ] [v1] Wed, 15 Jul 2026 16:17:58 UTC (4,844 KB) [v2] Mon, 20 Jul 2026 20:30:04 UTC (4,844 KB) [v3] Fri, 21 Aug 2026 23:00:00 UTC (4,844 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-07 Change to browse by: cs cs.IR References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning#665855
• Heterogeneity in neural network engagement supports individual differences in top-down attention#279913
• Measuring Time-Horizon Engagement Effectiveness: Persistence, Recency, and Re-Emergence#1083906
• Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling#363259
• Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences#1156216