Latest Information Retrieval Research Papers

The newest Information Retrieval papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Information Retrieval 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

• Generative Archetype-Grounded Item Representations for Sequential Recommendation
  Yifan Li, Jiahong Liu, Xinni Zhang, Hao Chen et al. · arXiv · Jun 9, 2026

  Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models…

• From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web
  Michael Iannelli, Alan Ai · arXiv · Jun 9, 2026

  When a conversational assistant recommends a brand to a user with no recent observed engagement, that user's same-name Google search rises +4.3 percentage points (pp) [3.1, 5.5], visits to the brand's own site +2.4 pp [1.4, 3.5], and brand-…

• Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
  Gal Bloch, Ariel Gera, Matan Orbach, Ohad Eytan et al. · arXiv · Jun 9, 2026

  We present \textbf{Flash-GMM}, a fused Triton kernel for efficient computation of Gaussian Mixture Models (GMMs) over large-scale data in a single GPU pass. By eliminating the need to materialize the full responsibility matrix in GPU memory…

• ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval
  Taiheng Pan · arXiv · Jun 9, 2026

  We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top-10 candidate set. v2 is a fine-tuned ms-marco-MiniLM-L-6-v2 cross-encoder (22,713,601 p…

• miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity
  Yingqi Fan, Xuan Lu, Anhao Zhao, Junlong Tong et al. · arXiv · Jun 9, 2026

  Multimodal large language models (MLLMs) have recently shown strong potential as point-wise rerankers by directly modeling query--document relevance through next-token prediction. However, point-wise reranking suffers from substantial repea…

• Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
  João Coelho, João Magalhães, Bruno Martins, Chenyan Xiong · arXiv · Jun 9, 2026

  The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards. With these algorithms, a query contributes to parameter updates only when its rollout group mixes successes and fai…

• Beyond Patches: Superpixel Token-based Transformers for Attribute-Specific Fashion Retrieval
  Shuili Zhang, Hongzhang Mu, Wenyuan Zhang, Duohe Ma et al. · WWW · Jun 9, 2026

  Attribute-Specific Fashion Retrieval (ASFR) aims to improve fine-grained image retrieval by focusing on specific attributes. However, existing patch-based attention and Transformer methods often misalign with irregular attribute regions and…

• STORM: Stepwise Token Optimization with Reward-Guided Beam Search
  Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong, Habiboulaye Amadou Boubacar et al. · arXiv · Jun 9, 2026

  Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever the model changes. Lexical retrievers like BM25 stay efficie…

• Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting
  Kazuki Nakayashiki, Keisuke Watanabe · arXiv · Jun 9, 2026

  Does personalizing what a reader sees pay off, and where does it stop? Using a social web highlighter and a co-readership identity control (the same document highlighted by many users, which holds document and topic fixed and asks whether a…

• SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval
  Jiandong Ding · arXiv · Jun 9, 2026

  Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes skill retrieval more than broad relevance matching. A …

• Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
  Ruobing Jiang, Dawei Fu, Cheng Jiang, Tianyi Yang et al. · arXiv · Jun 9, 2026

  Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature. As high-energy physics (…

• SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers
  Jiandong Ding, Heng Chang, Huijie Qin, Tianying Liu · arXiv · Jun 9, 2026

  Semantic-ID (\sid) tokenizers are increasingly reused as standalone artifacts in generative recommendation: an exported item-to-code mapping becomes the address space that a later sequence generator must use. These mappings rarely come with…

• Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
  Zhuohang Jiang, Yuxin Chen, Shijie Wang, Haohao Qu et al. · KDD · Jun 9, 2026

  Cross-domain recommendation is a core problem in content-to-e-commerce platforms. Its objective is to leverage user interactions with content to infer potential purchasing intent on the e-commerce side, thereby enhancing conversion rates an…

• $τ$-Rec: A Verifiable Benchmark for Agentic Recommender Systems
  Bharath Sivaram Narasimhan, Karthik R Narasimhan · arXiv · Jun 8, 2026

  As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on "LLM-as-a-judge" evaluations, which introduce subjectivity, high cost…

• MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention
  Asiful Arefeen, Carol Johnston, Hassan Ghasemzadeh · arXiv · Jun 8, 2026

  Postprandial hyperglycemia is a key risk factor for metabolic disorders; however, existing dietary guidance is often static, impractical, and insufficiently personalized, providing recommendations that are difficult to follow or not impactf…

• Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
  Yaochen Zhu, Harald Steck, James McInerney, Aditya Sinha et al. · arXiv · Jun 8, 2026

  Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences. In recommender systems, however, user feedback is rarely pairwise. For a given context, e.g., …

• Stability in Competitive Search with Results Diversification
  Itamar Reinman, Omer Madmon, Moshe Tennenholtz, Oren Kurland · arXiv · Jun 8, 2026

  In a competitive search setting, publishers strategically modify their documents in response to induced rankings so as to improve their future ranking. We present a novel game-theoretic analysis of a competitive search setting where search-…

• Popcorn: A Configurable Benchmark for Visual Evidence in Multimodal Movie Recommendation
  Ali Tourani, Fatemeh Nazary, Yashar Deldjoo, Tommaso Di Noia · arXiv · Jun 8, 2026

  Movies are long-form audiovisual works, yet recommender benchmarks often rely on trailers, thumbnails, or metadata. These sources differ in semantics and scalability: full movies preserve consumption-level evidence, trailers concentrate pro…

• TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs
  Momina Ahsan, Sarfraz Ahmad, Ming Shan Hee, Roy Ka-Wei Lee et al. · arXiv · Jun 8, 2026

  Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table reasoning tasks, but the role of table representation remains under-explored. In practice, the same table content may appear in different str…

• Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
  Yufei Chen, Zihan Wang, Yubao Tang, Yukun Zhao et al. · arXiv · Jun 8, 2026

  Multimodal generative retrieval formulates multimodal retrieval as discrete identifier generation, eliminating the need for explicit similarity search over external embeddings. Existing approaches construct identifiers via residual quantiza…

• Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
  Yufei Chen, Zihan Wang, Yubao Tang, Yukun Zhao et al. · arXiv · Jun 8, 2026

  Multimodal generative retrieval formulates multimodal retrieval as discrete identifier generation, eliminating the need for explicit similarity search over external embeddings. Existing approaches construct identifiers via residual quantiza…

• Driving Video Retrieval for Complex Queries with Structured Grounding
  Manyi Yao, Sparsh Garg, Christian Shelton, Amit Roy-Chowdhury et al. · arXiv · Jun 8, 2026

  Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins and hard braking. Existing vision-language and keyword-based …

• Teach Multimodal Recommendation Model to See via Personalized Visual Extraction and Adaptive Learning
  Yutong Li, Xinyi Zhang, Ziyi Ye, Daoguo Dong et al. · arXiv · Jun 8, 2026

  Multimodal sequential recommendation (MSR) incorporates textual and visual information to improve recommendation quality. However, recent studies and our empirical analysis show that visual features are often underutilized, thereby contribu…

• Decoy-Calibrated Failure Audits for Language Models
  Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh · arXiv · Jun 8, 2026

  Useful audits reveal not only how often a model fails, but also where its failures concentrate. An auditor may test many candidate explanations: long inputs, indirect questions, distracting evidence, or combinations of these factors. The ri…

• Personal Salience: Highlighting Is Social, but Individuality Lives in Selection
  Kazuki Nakayashiki, Keisuke Watanabe · arXiv · Jun 8, 2026

  Social highlighters let people mark passages that matter to them. We ask how much of an individual is recoverable from these naturalistic traces, using a co-readership identity control (the same document highlighted by many users) that hold…

• EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
  Hongwei Zhang, Xiaoman Wang, Zehui Ling, Ruicheng Zhu et al. · arXiv · Jun 8, 2026

  Retrieving evidence pages from visually rich long documents is a key challenge in document question answering. Existing page-level visual retrievers operate under an independent matching paradigm: each page is scored in isolation based on q…

• Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)
  Yifan Liu, Jaime Arguello, Orland Hoeber, Chang Liu et al. · arXiv · Jun 8, 2026

  This report summarizes the CHIIR 2026 Workshop on Generative AI and Academic Search (GAI\&AS), which examined how GenAI is reshaping academic search systems and research practices. The workshop brought together researchers in human info…

• Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors
  Yong Fu · arXiv · Jun 7, 2026

  We present HNTL (Hierarchical No-pointer Tangent-Local), the core vector indexing and candidate generation framework of the Aperon vector memory system. Proximity graphs (e.g., HNSW) incur a heavy pointer tax in memory overhead and induce i…

• Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations
  Daria Tikhonovich, Oleg Sorokin, Vladislav Dodonov, Mariia Ulianova et al. · arXiv · Jun 7, 2026

  Generative retrieval (GR) has become a scalable approach to candidate generation: each item is assigned a short hierarchical token sequence called a Semantic ID (SID), and the next item's SID is decoded autoregressively. A practical limitat…

• Detection and Interpretability Analysis of Quotation Errors by Large Language Models
  Bei Huang, Yingyi Zhang, Shenghao Huang, Chengzhi Zhang · arXiv · Jun 7, 2026

  Purpose - Quotation error refers to the inconsistency between cited information and its original source. This phenomenon leads to a series of negative impacts, such as misinterpretation of the original research, undermining the academic com…