cs.IR · 2026-08-24 · No. 94

Information Retrieval, 2026-08-24.

5 new papers in cs.IR. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

5 entries
  1. 01

    Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation

    Zichun Jin, Zihan Zhou, Yinan Liu, Bin Wang, Xiaochun Yang

    cs.IR · cs.AI

    Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equally informative. Real logs combine persistent preferences with temporary needs, exploration, and incidental behavior, so some interactions can distort history representations or provide unreliable supervision. Existing denoising methods judge such interactions mainly from co-occurrence, order, or model predictions, without...

    arxiv.org/abs/2608.21243 · PDF

  2. 02

    Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

    Yuyuan Feng, Zhishang Xiang, Chaobin Yang, Qichao Ma, Zerui Chen, Yujing Zhang, Ke Huang, Chuanjie Wu, Zhaoxu Liu,...

    cs.IR · cs.AI · cs.ET

    LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to organize external tools and resources, and Loop Engineering to support continual reflection and self-improvement. Yet as tasks grow more complex, individual intelligence...

    arxiv.org/abs/2608.21156 · PDF

  3. 03

    From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation

    Tianlu Xie, Xin Ku, Mingjie Sun, Yunhao Sha, Lixiang Wang, Peng Wang, Yiyu Wang, Wenjin Wu, Zhaojie Liu, Peng Jiang, Wenwu Ou

    cs.IR · cs.LG

    Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Typical systems use multi-level residual quantization, which increases autoregressive decoding cost and creates a large hierarchical space that may be sparsely occupied. Static codebooks also become misaligned with current traffic as new items arrive and exposure distributions change. We propose a...

    arxiv.org/abs/2608.21012 · PDF

  4. 04

    Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders

    Dojun Hwang, Seunghan Lee, Cheonyoung Park, Sara Yu, SeongKu Kang

    cs.IR · cs.AI · cs.CL

    While Large Language Models (LLMs) have significantly advanced reranking in recommendation, effectively leveraging item-side information remains challenging. Real-world items are described by vast, heterogeneous, and unstructured metadata, where decision-relevant signals are often implicit, noisy, or buried in long descriptions. Moreover, feature salience is highly context-dependent, varying not only across items but also across users....

    arxiv.org/abs/2608.20801 · PDF

  5. 05

    One Hierarchy, Two Systems: Semantic Product IDs for Discovery-Surface Ranking and Search-Page Query Reformulation

    Steven Xu, Sanjyot Thete, Saathvik Dirisala, Raghav Saboo, Nimesh Sinha, Leo Shao, Elyse Winer, Sudeep Das, Martin...

    cs.IR · cs.AI

    Multi-merchant e-commerce catalogs contain equivalent and related products under different merchant-scoped identifiers, fragmenting behavioral evidence across merchants. Expert-defined taxonomies, meanwhile, are often too coarse for fine-grained discovery. We investigate whether a single hierarchical Semantic ID (\sid{}) representation can support personalized ranking and query reformulation. Learned once from product-content embeddings, the...

    arxiv.org/abs/2608.20640 · PDF

This edition is part of The Daily Abstract — cs.IR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.