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

• FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation
  Mingzhe Han, Jiahao Liu, Dongsheng Li, Jiankui Zhou et al. · arXiv · Sep 10, 2026

  Federated recommendation enables collaborative model training while keeping user interaction data on local clients. A central problem in federated recommendation is how to aggregate useful information across clients for personalized recomme…

• UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems
  Lingyuan Kong, Jiaqi Cui, Fanjiao Zeng, Congqi Wang et al. · arXiv · Sep 10, 2026

  Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items …

• Following the Preference, Missing the Optimum: Compliance Without Optimization in AI Housing Recommendation
  Hsuan Lo · arXiv · Sep 9, 2026

  Large language models are becoming the first point of contact for consumer search in domains where the stakes are material and the law is explicit. Existing audits show that models steer housing seekers by perceived identity, but none can s…

• Purchase Advice and Observable Buyer Responses in Real AI Conversations
  Benjamin Tannenbaum · arXiv · Sep 9, 2026

  How often does a generative assistant persuade someone to buy, or persuade them not to buy? Conversation logs contain recommendations, but they do not necessarily record subsequent decisions. We audit 317 historical interactions from Aiso's…

• FINALLY: A Dataset Recommender System for Recommender-Systems Research
  Louis Owie · arXiv · Sep 8, 2026

  Dataset selection shapes the empirical conditions under which recommender-system algorithms are evaluated, yet existing tools provide limited support for constructing complete dataset sets that jointly satisfy experimental constraints and s…

• SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
  Lin Guan, Jia-Qi Yang, Zhishan Zhao, Jiaqi Huang et al. · arXiv · Sep 8, 2026

  Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking models operate under strict latency, memory, communication, and training-throughput constraint…

• Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones
  Yuchen Wang, Feng Niu, Qing Tan, Junting Lu et al. · arXiv · Sep 7, 2026

  Industrial ranking models for recommendation have scaled feature interaction and sequence modeling separately; recent architectures such as HyFormer and MixFormer unify both in a stackable backbone. Real-world recommender systems, however, …

• EAGER: Enrich-and-Align Generative Query Recommendation from Clicked Items in E-commerce Search
  Shuwei Yuan, Mingqian Ding, Luxin Liu, Rong Xiao et al. · arXiv · Sep 7, 2026

  E-commerce platforms increasingly display clickable query suggestions alongside items in the user feed, enabling users to refine or expand their intent without manually reformulating queries. Existing approaches either mine suggestions from…

• FunnelAudit: Responsibility Auditing in Multi-Route Recommender Systems
  Jie Li, Dudu Luo, Jiayang Niu, Ke Deng et al. · arXiv · Sep 7, 2026

  Multi-route recommender systems combine retrieval, allocation, fusion, and ranking, making individual inclusions and exclusions difficult to audit. Route overlap can hide effects from one-at-a-time ablations, while freezing downstream stage…

• Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
  Maddalena Amendola, Antonio Mallia, Raffaele Perego · arXiv · Sep 4, 2026

  Dense retrieval systems are core components of modern search engines, recommendation platforms, and retrieval-augmented generation pipelines. They encode documents and queries into dense embeddings, enabling efficient semantic search via ve…

• Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro
  Aleksandra Osowska-Kurczab, Klaudia Nazarko, Eliška Kosturová, Lidia Wojciechowska et al. · arXiv · Sep 4, 2026

  When a customer adds a professional camera to their cart, should the system suggest a matching lens, a generic tripod, or another camera body? Complementary Product Recommendation is vital for comprehensive basket building, yet standard mod…

• Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources
  Dmitrij Żatuchin · arXiv · Sep 4, 2026

  Whether repeated identical buying questions exhaust a language model's brand recommendations depends on retrieval. Across 300 question-engine cells (50 questions, six engines, 15 runs each, open extraction over 1,470 adjudicated organizatio…

• AtomRec: Evolving Atomic Memory for Agentic Recommendation
  Peiyu Hu, Weihai Lu, Siying Gu, Zhuodong Liu et al. · arXiv · Sep 4, 2026

  Agentic recommender systems use large language models to maintain semantic memory and support evidence-aware recommendation. However, existing memory mechanisms often compress user and item information into coarse summaries and connect them…

• Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation
  Fuyuan Liu, Tiandeng Wu, Yaqun Fang, Wei Zhou et al. · arXiv · Sep 4, 2026

  Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths ac…

• Latent-Aligned Reasoning for Multimodal Recommendation
  Jiarui Jin, Anyang Ji · arXiv · Sep 4, 2026

  Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet a fundamental challenge persists when applying them to recommendation: as representations propagate through multi-step reas…

• MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning
  Ahmad Mousavi, Majid Alikhani, Yeon-Chang Lee, Roberto Corizzo et al. · arXiv · Sep 4, 2026

  Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current architectures face two bottlenecks: structural rigidity, from a reliance on static precomputed…

• The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations
  Dmitrij Żatuchin · arXiv · Sep 3, 2026

  Background: Researchers increasingly use repeated identical prompts to audit stochastic variation in large language model (LLM) brand recommendations, yet no standardized protocol exists for setting iteration counts, selecting stability met…

• EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation
  Tuan-Binh Tran, Thanh Tam Nguyen, Quoc Viet Hung Nguyen, Dung D. Le et al. · arXiv · Sep 3, 2026

  Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete tokens. Recent masked-diffusion methods improve this process through bidirectional context and flexible decoding, yet recommendation …

• HypRQ-VAE: Hyperbolic Item Indexing for Long-Tail-Aware Generative Recommender Systems
  Longfeng Wu, Tong Zeng, Giovanni Seni, Zhimin Peng et al. · arXiv · Sep 3, 2026

  Sequential recommender systems model user behavior as item ID sequences, while recent generative methods cast recommendation as a language modeling task using large language models (LLMs). While this paradigm incorporates rich textual seman…

• SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation
  Chumeng Jiang, Jiayin Wang, Xinjie Lin, Zhiqiang Guo et al. · arXiv · Sep 3, 2026

  Large Language Models (LLMs) have recently emerged as powerful backbones for recommendation. To better elicit their capabilities, reasoning has been widely incorporated to help LLMs interpret rich textual signals and improve recommendation …

• UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction
  Jiajun Cui, Zhengqi Xu, Fan Zhang, Zhangteng et al. · arXiv · Sep 3, 2026

  Unified modeling has become a major direction for industrial click-through rate (CTR) prediction. Existing approaches typically unify sequential and non-sequential signals at the token level, model their interactions in a shared backbone, a…

• Recommender System as Slow and Fast Thinkers
  Zichen Yuan, Xiaoxuan Dong, Linkun Dai, Jinwei Yang et al. · arXiv · Sep 2, 2026

  Sequential recommendation models are foundational to modern personalized services, yet their effectiveness varies substantially across heterogeneous user environments. In particular, static one-pass recommenders often perform well on common…

• Training seeds and model-selection stability in recommender-system evaluation
  Juan Manuel Rodriguez, Oleg Lesota, Antonela Tommasel · arXiv · Sep 2, 2026

  Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation conclusions. This assumption is risky, as a training seed may influence several algorithm-de…

• GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation
  Qianqian Wang, Yunshan Li, Jiawen Zeng, Wenwu Gong et al. · arXiv · Sep 2, 2026

  Serving useful recommendations under distribution shift is crucial for balancing utility and risk in out-of-distribution (OOD) recommendation. However, most existing OOD methods improve ranking or construct counterfactual candidates without…

• Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation
  Jialin Liu, Zhaorui Zhang, Ray C. C. Cheung · arXiv · Sep 2, 2026

  Multimodal Recommender Systems (MRSs) typically rely on a flawed "modality harmony" assumption, presuming that multimodal features are inherently beneficial and strictly aligned with users' collaborative interaction patterns. However, modal…

• SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception
  Fangye Wang, Yunjin Gu, Haowen Lin, Yifang Yuan et al. · arXiv · Sep 2, 2026

  Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's semantic ID (SID), holds great promise for Location-Based Services, where a recommendation helps only if the user can reach it. Yet, existing meth…

• From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs
  Jie Chen, Xiangqian Yu, Yanchao Lian, Tan Lu et al. · arXiv · Sep 1, 2026

  Scaling Transformers has driven large gains in language modeling, but transplanting this to behavior-sequence modeling in production ranking is challenging: recommendation differs in signal quality, where behavior sequences are noisy, tempo…

• TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning
  TGR Team, Lei Cheng, Haonan Hu, Beibei Kong et al. · arXiv · Sep 1, 2026

  Industrial recommender systems typically rely on cascaded retrieval, pre-ranking, ranking, and reranking stages, whose separately optimized models limit scaling, fragment decision making, and lack semantic knowledge and reasoning. We presen…

• SwapRec: Warming Up Cold Items Through Training-Time Swaps
  Marta Moscati, Jan Malte Lichtenberg, Davide Abbattista, Antonio De Candia et al. · arXiv · Sep 1, 2026

  Interactions with cold items negatively impact real-time personalization of ID-based recommender systems. This is because the use of such interactions degrades user preference estimates, whereas excluding cold items from the user profile pr…

• Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
  Jincheng Zhang, Chen Huang, Wenqiang Lei, See-Kiong Ng et al. · arXiv · Sep 1, 2026

  We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose DREAMS, a novel tree-structured context modeling framework that explicitly c…