cs.IR · 2026-07-29 · No. 68

Information Retrieval, 2026-07-29.

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

    Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs

    Chandan Kumar Sah, Xiaoli Lian, Li Zhang

    cs.IR · cs.AI · cs.CL

    Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation. We investigate whether verbalized confidence from black-box language models can serve as an actionable signal for retrieval routing. Our method, BeyondUncertainty, first elicits a structured provisional answer and confidence estimate, then applies a model-specific threshold...

    arxiv.org/abs/2607.25600 · PDF

  2. 02

    MARS: Multi-Agent Re-ranking for Repeat-Order Food Delivery Recommendation

    Jiahao Tian, Zhenkai Wang

    cs.IR · cs.AI

    Large language models (LLMs) are increasingly used in recommender systems, but it is often unclear how much performance can be obtained from strong pre-trained backbones alone when they are placed inside a structured recommendation pipeline. In this paper, we present MARS, a modular multi-agent re-ranking framework for repeat-order food delivery recommendation. MARS serves as a controlled hybrid framework for studying how far pre-trained LLMs...

    arxiv.org/abs/2607.25420 · PDF

  3. 03

    Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation

    Huwei Ji, Jiajie Su, Yuyuan Li, Xiaohua Feng, Chaochao Chen

    cs.IR · cs.LG

    LLM-based Cross-Domain Sequential Recommendation (CDSR) leverages LLMs to enhance target performance via deep semantic reasoning, alleviating the dependency on overlapping users. Among LLM-based paradigms, model merging is particularly promising for multi-domain scenarios due to its superior scalability and flexibility in integrating diverse knowledge sources. However, our empirical investigations reveal two critical bottlenecks: (1)...

    arxiv.org/abs/2607.25366 · PDF

  4. 04

    Structure-aware Relative Policy Optimization for Ranking

    Yiteng Tu, Weihang Su, Zitao Su, Yiqun Liu, Min Zhang, Qingyao Ai

    cs.IR · cs.AI

    Ranking is a fundamental component of modern information access systems. Reinforcement learning (RL) provides a flexible framework for directly optimizing coarse-grained feedback and system-level objectives defined over the complete ranking list. However, existing RL-based ranking methods typically treat each sampled permutation as an atomic output and evaluate it primarily through a scalar reward, overlooking the structural relationships...

    arxiv.org/abs/2607.25268 · PDF

  5. 05

    TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation

    Ziyu Zheng, Zhengshun Du, Yaming Yang, Bin Tong, Guan Wang, Meng Yan, Ziyu Guan, Wei Zhao

    cs.IR · cs.AI

    Semantic ID-based generative recommendation tokenizes each item into a sequence of discrete semantic IDs and predicts the next item by generating semantic IDs. However, existing methods typically regard SIDs as independent discrete symbols, while often overlooking the topology of the learned semantic ID space. We identify a structural mismatch between tokenization and generation: the tokenizer learns a structured code space with semantic...

    arxiv.org/abs/2607.25216 · 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.