cs.IR · 2026-09-15 · No. 114

Information Retrieval, 2026-09-15.

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

01 — The papers

3 entries
  1. 01

    Self-Evolving Memory for Generative Recommendation

    Xinyu Lin, Zhuosong Jiang, Zixiao Suo, Siqin Wang, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh,...

    cs.IR · cs.AI

    Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolve over time, making self-evolving an essential capability for generative recommender systems. Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters using streaming interactions. Nevertheless, we find that...

    arxiv.org/abs/2609.15598 · PDF

  2. 02

    Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA

    Luis M. Sánchez

    cs.IR · cs.AI · cs.CL · q-fin.GN

    Frontier models score well on shallow document/chart reading tasks. In a controlled data-room audit, moving evidence into buried conditions reduced accuracy, increased forced declarations, increased tool calls, and increased cost per correct answer. Confidence and benchmark calibration did not fully capture wrong answers; a documented production incident shows fabricated structural claims can be mixed with accurate numeric tables. Agentic...

    arxiv.org/abs/2609.15319 · PDF

  3. 03

    Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation

    Yi Chen, Rufeng Cheng, Qiang Xie, Tao Li

    cs.IR · cs.AI

    In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user population, particularly suppressing the needs of long-tail audiences. While Large Language Models (LLMs) have been integrated into recommendation for content understanding or ranking, directly optimizing them to output a single best headline typically leads to mode collapse---converging to generic...

    arxiv.org/abs/2609.15094 · 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.