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

• R2QRec: Learning Recommendation Queries from Retrieval Feedback
  Weixin Chen, Shuchang Liu, Hailan Yang, Yuhan Zhao et al. · arXiv · Oct 29, 2026

  Query-based recommendation separates expressing user needs from locating matching items. Its central learning problem is how to turn item interactions into effective retrieval requests when interaction logs do not annotate queries. We prese…

• RoFiGR: Coarse Routing, Fine Refinement via Level-Adaptive Distillation in Multimodal Generative Recommendation
  Ji Dai, Zhipeng Wei, Zhuang Zhuang, Rongfeng Guo et al. · arXiv · Oct 29, 2026

  Generative recommenders predict an item's semantic identifier (SID) one code at a time. Early codes select broad branches, so a routing error can exclude relevant items before fine-grained prediction begins. In multimodal recommendation, th…

• UGR: Unified Generative Ranking for Heterogeneous E-commerce Recommendation
  Zonghe Shao, Huabin Chen, Sitong Lu, Fangmei Zhu et al. · arXiv · Oct 29, 2026

  List-wise ranking in e-commerce recommendation must balance user utility and commercial value across organic content, ads, and candidates from other businesses, while modeling candidate interactions and sequential dependencies. Existing gen…

• Try Before You Evolve: Ranking-Scored Trials for Recursive Self-Improvement of Recommender Systems
  Xu Huang, Jiawei Feng, Jiancan Wu · arXiv · Oct 29, 2026

  Recommenders on Web platforms such as e-commerce and music streaming need their training recipes re-tuned for each dataset. Large language model (LLM) agents can now rewrite these recipes, enabling recursive self-improvement (RSI) of recomm…

• Federated Recommender Agents
  Jaehyung Lim, Woojoo Kim, Junyoung Kim, Dongha Kim et al. · arXiv · Oct 29, 2026

  LLM-powered recommender agents use reasoning and memory for personalization, but centralized access to user information raises privacy concerns, while isolated agents cannot learn from others' experiences. We formulate Federated Recommender…

• PFA: Attention Can Be Progressively Focused in Long-Sequence Generative Recommendation
  Pengjie Zhou, Weiqin Yang, Haibo Xing, Hao Deng et al. · arXiv · Oct 29, 2026

  Long user behavioral sequences improve the performance of generative recommendation (GR), but computing full attention over long histories during autoregressive beam search decoding incurs substantial online inference latency. To accelerate…

• Read More, Reason Deeper: Latent Workspaces for Long-Sequence Recommendation
  Renzhi Wu, Li Sheng, Zikun Cui, Junjie Yang et al. · arXiv · Oct 29, 2026

  Long-sequence recommendation can improve along two axes: \emph{evidence scaling} exposes longer histories, while \emph{reasoning scaling} adds layers that interpret that evidence for a candidate. Existing models couple them: sequence encode…

• PRISM: Personalized Item Representations in User History
  Renzhi Wu, Zikun Cui, Junjie Yang, Li Sheng et al. · arXiv · Oct 29, 2026

  Sequential recommenders typically construct history inputs from item identifiers or content features using an embedding map shared across users. The same item therefore yields the same initial embedding representation, even when users have …

• Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising
  Yatong Xiao, Yibo Sheng, Lixiang Wang, Mingjie Sun et al. · arXiv · Oct 28, 2026

  Generative recommendation (GR) reformulates item retrieval as autoregressive generation of discrete semantic identifiers (SIDs), offering a unified paradigm for personalized recommendation. GR4AD, as an industrial generative recommendation …

• Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation
  Yunqin Zhu, Yao Xie · arXiv · Oct 27, 2026

  LLM-based generative recommendation reads long, text-rich interaction histories but generates only short semantic identifiers (SIDs). This asymmetry makes supervised fine-tuning inefficient: encoding the history is expensive, yet each histo…

• Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence
  Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos · arXiv · Oct 27, 2026

  Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This flexible design introduces new sources of structural bias. This paper …

• What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine
  Saransh Kumar Gupta, Akshadha Sharma, Lipika Dey, Partha Pratim Das et al. · arXiv · Oct 27, 2026

  Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation. We ask what happens to food similarity beyond identity: how differ…

• REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation
  Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li et al. · arXiv · Oct 27, 2026

  Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete s…

• REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation
  Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li et al. · arXiv · Oct 27, 2026

  Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete s…

• Can Complementary Signals Bridge Similarity Islands? Manifold-Augmented Graph Embedding for Multimodal Recommendation
  Zhenye Yang, Jinpeng Chen, Wenbo Fu, Jun Ma et al. · arXiv · Oct 27, 2026

  Multimodal Recommender Systems (MMRS) leverage rich item features to mitigate data sparsity, yet similarity-driven graph construction and propagation can favor semantically similar substitutes over functionally related complements. When beh…

• LESSRec: Level-Specific History Modeling for Semantic ID-Based Recommendation
  Shangxin Yang, Zongwei Wang, Jing Long, Junliang Yu et al. · arXiv · Oct 27, 2026

  Semantic ID-based recommendation represents each item as a sequence of semantic tokens obtained through residual quantization. This paradigm generates the next item's tokens autoregressively from coarse to fine, entailing each prediction at…

• Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation
  Mingzhe Lu, Jian Qin, Ruize Qin, Jinhao Liu et al. · arXiv · Oct 27, 2026

  Narrative-driven recommendation allows users to express multifaceted needs through free-form text where stated preferences naturally qualify and condition one another. Existing methods typically treat narratives as flat keyword combinations…

• AutoRSE: Evaluating LLM Agents as Recommendation Engineers for Self-Evolving Recommender Systems
  Rui Tian, Yi Fang, Yejin Hua, Du Wang et al. · arXiv · Oct 27, 2026

  Recommender Systems Engineer Agents (RSE-Agents), which use LLM-based agents to autonomously improve recommendation algorithms, are emerging as a promising paradigm. However, their capabilities and limitations remain poorly understood due t…

• Rethinking Positional Encoding and Interaction Granularity for CTR Prediction
  Xinxun Zhang, Yuxiang Wang, Xiaokai Zhou, Jiayue Li et al. · arXiv · Oct 27, 2026

  Click-through rate (CTR) prediction relies on historical behaviors and contextual features to estimate clicks on a target item. Existing Transformer-based CTR models often adopt index-based or temporal positional encodings and token-level c…

• Compote: Collapse-Resistant Multiple Hypothesis Learning For Sequential Recommendation
  Louis Castres Saint Martin, Clement Calauzenes, Alain Rakotomamonjy, Patrick Gallinari · arXiv · Oct 27, 2026

  Next-item prediction is inherently ambiguous: a single interaction history often admits multiple plausible continuations across distinct catalogue regions. Standard sequential recommenders compress these alternatives into a single predictio…

• KL-MOPD: Discrepancy-Aware Multi-Objective On-Policy Distillation for Generative Recommendation
  Weiqin Yang, Yandong Wang, Yuan Gao, Hao Deng et al. · arXiv · Oct 27, 2026

  Coordinating multiple recommendation objectives (e.g., click and conversion) is critical for real-world generative recommendation (GR). However, since a positive item in GR can be retrieved only when its tokens are successively selected at …

• PailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search
  Xiaohan Ye, Zihan Gong, Jingqian Zhao, Lianyu Du et al. · arXiv · Oct 27, 2026

  Generative retrieval models have been increasingly adopted in search and recommendation systems. However, industrial generative retrieval models are commonly specialized to a fixed online scenario: they learn from scenario-specific interact…

• When Diffusion Recommenders Stop Sampling: Preserving Generative Diversity
  Louis Castres Saint Martin, Alain Rakotomamonjy, Patrick Gallinari · arXiv · Oct 27, 2026

  A user history can admit multiple plausible next interactions, yet conventional sequential recommenders produce a single deterministic ranking. While diffusion models offer a natural way to sample alternative continuations, we show that exi…

• Latent Residual Reasoning for Ranking in Generative Recommendation
  Haihan Shi, Ruidong Han, Wenjie Wang, Shangyu Chen et al. · arXiv · Oct 27, 2026

  Generative recommendation (GR) models for ranking typically adopt a fast-thinking direct prediction paradigm with strong practical efficiency. However, ranking requires fine-grained scoring across multiple candidate items, while existing GR…

• DuTri: Dual-Branch Modeling with Triadic Factorization for Multimodal Multi-Scenario Recommendation
  Jintao Huang, Chaohua Yang, Kailiang Hao, Dugang Liu et al. · arXiv · Oct 27, 2026

  As recommendation scenarios become increasingly diverse and multimodal information grows more prevalent, effectively modeling cross-scenario user preferences and multimodal semantics has become a critical challenge in recommender systems. W…

• The Vocabulary Is Already Here: Adapting Pretrained Interpretable Features for Generative Recommendation
  Ziluowen Luo, Ruochen Liu, Jun Yin, Hao Yan et al. · arXiv · Oct 27, 2026

  Generative recommendation (GR) predicts the next item through its semantic ID (SID). Existing methods commonly fit SID vocabularies to pretrained language model (PLM) representations of item descriptions, incurring additional training costs…

• MAREval: A Multi-Agent Framework for Evaluating Natural Language Recommendation Explanations
  Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Aysenur Inan, Ramin Giahi et al. · arXiv · Oct 26, 2026

  Evaluating natural language explanations in recommender systems is essential for fostering user trust, transparency, and engagement. However, existing evaluation approaches like human evaluations, while accurate, are resource-intensive and …

• Preserving rare-item recall under a storage budget: quantization, distillation, and the limits of teacher fidelity
  Han Chen, Yingrui Li · arXiv · Oct 26, 2026

  Under a fixed embedding-storage budget, recommenders can use a small full-precision model, a distilled student, or a higher-rank low-precision model. We asked which choice preserves rare-item recall and whether teacher fidelity reflects it …

• BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals
  Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Selene Xu et al. · arXiv · Oct 26, 2026

  Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term histor…

• Counterfactual Profile Perturbations for Recommendation Explanations: A Reproducibility Study
  Meysam Varasteh, Elizabeth McKinnie, Robin Burke · arXiv · Oct 26, 2026

  This reproducibility paper explores the counterfactual explanation technique known as Learning to eXplain Recommendations (LXR). Prior work has shown that LXR can reliably identify perturbations that, if applied to a user's profile, cause t…