Latest Recommendation Systems Research Papers

The newest Recommendation Systems papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Recommendation Systems so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Diffusion Language Model for Recommendation
  Chengyi Liu, Yongqi Zhou, Junwei Pan, Zhixiang Feng et al. · arXiv · Jul 23, 2026

  Large language model (LLM)-empowered recommender systems have emerged as a promising paradigm for generative recommendation, leveraging their strong semantic reasoning and generative capacity to model complex, diverse user preferences. Howe…

• Transparent by Design, Usable in Practice? A Formative Usability Study of a Conversational Product Advisor
  Kevin Schott, Dagmar Kern, Daniel Hienert · arXiv · Jul 23, 2026

  Large language models can make conversational product advisors fluent but opaque. If they hide the logic behind a ranking and the evidence for a recommendation inside natural-language replies, they challenge users' ability to understand, tr…

• Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation
  Junchao Zeng, Junzhang Zhu, Junyang Chen, Yudong Li et al. · arXiv · Jul 23, 2026

  Generative Recommendation (GR) has emerged as a new paradigm for sequential recommendation, in which a representative line of work encodes items into hierarchical semantic IDs via residual quantization and predicts the IDs token by token. H…

• Controllable and Content-Based Recommendations
  Fırat Öncel, Jihoon Jeong, Emiliano Penaloza, Mirco Ravanelli et al. · arXiv · Jul 23, 2026

  Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendations (CCBR) framework, which builds its recommendations from…

• LO-FAR: A Cost-Aware Local Filter for Sparse Feature Ranking in Industrial Ad Recommendation
  Egemen Erbayat, Luis Duque, Sohini Roychowdhury, Mohammad Amin et al. · RecSys 2026 · Jul 23, 2026

  Industrial ad recommendation models rely heavily on sparse, high-cardinality ID-list features that encode user histories and contextual identifiers. Each is backed by a dedicated embedding table, so these features dominate storage, training…

• Probabilistic Residual Learning for Online Recommendations
  Wenyuan Wang, Yusong Zhao, Zihao Xu, Hengyi Wang et al. · arXiv · Jul 23, 2026

  Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffer from the black-box nature and computational complexity of …

• Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs
  Parul Maheshwari, Amulya Paruchuri, Yiqing Zou, Alireza Sahami Shirazi et al. · arXiv · Jul 22, 2026

  Graph Neural Networks trained on heterogenous bipartite graphs form a common basis in recommendation systems. These graphs often express relations that vary in cardinality, for example, user-item preferences are one-to-many and user-attribu…

• UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
  Honghao Li, Xianquan Wang, Zibin Zhang, Yi Zhang et al. · arXiv · Jul 22, 2026

  Ranking is a core stage in online advertising and recommender systems. Modern ranking models increasingly unify sequential modeling and feature interaction, yet many advances rely on proprietary data, closed implementations, and large-scale…

• UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
  Honghao Li, Xianquan Wang, Zibin Zhang, Yi Zhang et al. · arXiv · Jul 22, 2026

  Ranking is a core stage in online advertising and recommender systems. Modern ranking models increasingly unify sequential modeling and feature interaction, yet many advances rely on proprietary data, closed implementations, and large-scale…

• Zero-Observation User Reactivation with Gap-Driven Dimensional Gating
  Jiandong Ding, Tianying Liu, Fuyuan Liu, Huijie Qin et al. · arXiv · Jul 22, 2026

  Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Observation Reactivation: the user has a pre-gap history, while …

• Personalized Recommendation Tool Learning via Autonomous Language Agents
  Mingdai Yang, Zhiwei Liu, Weizhi Zhang, Yibo Wang et al. · arXiv · Jul 22, 2026

  Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limi…

• Spectral Biclustering-Driven Scalability for Post-Hoc Explainability in Recommender Systems
  Jose L. Salmeron, Irina Arévalo · arXiv · Jul 21, 2026

  Explainability in recommender systems is essential for ensuring transparency, accountability, and trust, yet existing post-hoc methods often encounter severe scalability challenges. Observation-level deletion diagnostics offer a counterfact…

• Beyond Noisy Signals: Dual-Level Denoising for Multi-modal Sequential Recommendation
  Jie Luo, Qi Jin, Xinming Zhang · arXiv · Jul 21, 2026

  Multi-modal Sequential Recommendation (SR) incorporates rich side information (e.g., textual and visual features) to enhance dynamic user preference modeling. However, existing frameworks inevitably suffer from a \textbf{Dual-Noise Dilemma}…

• An Epistemic Position-Based Click Model: From Interactions to Epistemic Distributions of Relevance and Bias
  Oscar Rolando Ramirez Milian, Harrie Oosterhuis · arXiv · Jul 21, 2026

  User interactions with rankings are affected by both items' relevances and display positions. Accordingly, click probabilities are often modeled as a product of relevance and position factors; and for improving recommendation and search, on…

• Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation
  Yongsen Zheng, Ruilin Xu, Guohua Wang, Liang Lin et al. · arXiv · Jul 21, 2026

  The Matthew effect is a big challenge in Recommender Systems (RSs), where popular items tend to receive increasing attention, while less popular ones are often overlooked, perpetuating existing disparities. Although many existing methods at…

• Topology-Aware Tokenization for Generative Recommendation
  Yaokun Liu, Yifan Liu, Zhenrui Yue, Gyuseok Lee et al. · arXiv · Jul 21, 2026

  Generative recommendation reformulates sequential recommendation as an autoregressive generation task, yet a critical issue in this paradigm remains overlooked: topology distortion in item tokenization. In particular, we observe that the in…

• CoSimRec: Measuring Coordinated-Content Penetration in Recommender Feedback Loops
  Nan Li, Jiahong Shao, Jiuyang Lyu · arXiv · Jul 16, 2026

  Recommender systems increasingly shape which content reaches users, making it important to understand whether coordinated activity is amplified beyond the accounts that initiate it. Existing robustness evaluations largely focus on static ta…

• Impact of Expert-Following Strategies in Financial Asset Recommendation
  Ryuki Unno, Koshi Watanabe, Keigo Sakurai, Keisuke Maeda et al. · arXiv · Jul 16, 2026

  Financial institutions hold rich transaction histories, yet delivering recommendations that simultaneously maximize investment returns and ensure preference alignment remains a significant challenge. Existing approaches, namely return-based…

• Long-History User Transformers for Real-Time Ad Ranking
  Viacheslav Ovchinnikov, Georgii Smirnov, Nikolai Savushkin, Veronika Ivanova et al. · arXiv · Jul 15, 2026

  Long interaction histories are among the most informative inputs for click-through rate (CTR) prediction, yet in online advertising they collide with a hard serving constraint: ads must be scored within a few hundred milliseconds to enter t…

• Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning
  Dingsu Wang, Filip Ryzner, Kelly He, Armando Ordorica et al. · arXiv · Jul 15, 2026

  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 opt…

• User Preference Induction with LLMs for Offline Top-N Recommendation Evaluation
  David Otero, Javier Parapar · arXiv · Jul 13, 2026

  Offline evaluation is the standard methodology for comparing top-N recommender systems, yet it relies on incomplete relevance information. In most benchmark datasets, only a small subset of user--item preferences is observed, and unjudged i…

• Prompt Generation Technical Report
  Dan Ou, Gui Ling, Hao Wan, Hongbin Zhou et al. · arXiv · Jul 13, 2026

  Generative retrieval has become an increasingly adopted paradigm for industrial search, recommendation, and advertising systems, delivering significant online gains. Most existing work combines user behavior sequences with large language mo…

• Normative Alignment of Recommender Systems via Internal Label Shift
  Johannes Kruse, Kasper Lindskow, Michael Riis Andersen, Ryotaro Shimizu et al. · arXiv · Jul 12, 2026

  We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions over item-level attributes, such as categories. Recommender…

• ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
  Johannes Kruse, Ryotaro Shimizu, Kasper Lindskow, Jon Tofteskov et al. · arXiv · Jul 12, 2026

  We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deployment. ZoRRO outperforms strong neural baselines in offline ra…

• Stream-aware Side Adaptation for Large Pre-trained Multimodal Embedding Models in Sequential Recommendation
  Junchen Fu, Kaiwen Zheng, Ioannis Arapakis, Wenhao Deng et al. · arXiv · Jul 12, 2026

  Recently, large pretrained multimodal embedding models such as Qwen3-VL Embedding have shown strong promise for sequential recommendation, as they provide reusable semantic item representations across modalities and domains. However, direct…

• RecRec: Recursive Refinement for Sequential Recommendation
  Pervez Shaik, Prosenjit Biswas, Abhinav Thorat, Ravi Kolla et al. · arXiv · Jul 12, 2026

  Sequential recommender systems typically infer user preferences through single-pass encoding of interaction histories without iterative refinement, relying on increasingly deep architectures to capture complex patterns. In this work, we rev…

• From Raw IDs to Semantic Planning: How Recommender Systems Utilize Information at Scale
  Changhong Jin, Shiqiu Yang, Roger Zhe Li, Yingjie Niu et al. · arXiv · Jul 10, 2026

  The evolution of recommender systems can be explored by asking how they utilize information at scale. Throughout most of the historical period under consideration during the past two decades, industrial systems have relied on raw IDs, which…

• DaV-Gen: End-to-End Generative Retrieval via Draft-and-Verify
  Meng Zhao, Chunmei Liu, Qinyong Wang · arXiv · Jul 9, 2026

  Mainstream industrial information retrieval systems (e.g., search and recommendation) are usually built upon Multi-Stage Cascade Architectures (MCAs), which balance effectiveness and efficiency through a coarse-to-fine ``retrieval-ranking''…

• Seeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendation
  Hao Cong, Huizu Lin, Zihan Wang, Chengkai Huang et al. · arXiv · Jul 8, 2026

  Large language model (LLM)-based agentic recommender systems show promise in modeling user preferences through natural-language reasoning, yet they remain limited by text-centric inputs and coarse-grained memory updates, making agents prone…

• When and How to Ask: Dynamic Preference Elicitation Strategies for Conversational Recommendation
  Feng Xia, Shuo Zhang, Xi Wang · arXiv · Jul 7, 2026

  Conversational Recommender Systems (CRSs) are interactive systems that use multi-turn natural language dialogue to understand evolving user preferences and provide personalized recommendations. To achieve this goal, CRSs rely on preference …