ArXiv TLDR
← All categories

Information Retrieval

Papers on search engines, recommendation systems, and information extraction.

cs.IR · 379 papers

Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation

BLADE introduces a Bayesian framework for LLM-based recommenders to dynamically optimize list-wise metrics, outperforming static methods.

2605.04559May 6, 2026Ruijun Chen, Chongming Gao, Jiawei Chen +2

DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation

DoGMaTiQ automates the generation of high-quality, QA-based "nuggets" for evaluating RAG reports, showing strong correlation with human judgments.

2605.04458May 6, 2026Bryan Li, William Walden, Yu Hou +6

One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving

HELM adaptively partitions GPU HBM between embedding and KV caches for generative recommenders, reducing P99 latency by 24-38% across diverse workloads.

2605.04450May 6, 2026Wenjun Yu, Shuguang Han, Amelie Chi Zhou

Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems

This paper introduces BRIGHT-Pro, a new benchmark, and RTriever-Synth, a training corpus, to advance reasoning-intensive retrieval for agentic search systems.

2605.04018May 5, 2026Yilun Zhao, Jinbiao Wei, Tingyu Song +3

Domain-Adaptive Dense Retrieval for Brazilian Legal Search

This paper explores domain-adaptive dense retrieval for Brazilian legal search, finding a mixed training approach offers robust performance.

2605.04005May 5, 2026Jayr Pereira, Roberto Lotufo, Luiz Bonifacio

Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing

MAKA is a physics-grounded multi-agent AI architecture for traceable, risk-aware human-AI decision support in high-precision manufacturing.

2605.04003May 5, 2026Danny Hoang, Ryan Matthiessen, Christopher Miller +5

Aspect-Aware Content-Based Recommendations for Mathematical Research Papers

This paper introduces AchGNN, an aspect-conditioned GNN, and new datasets for content-based mathematical research paper recommendations, outperforming prior methods.

2605.03861May 5, 2026Ankit Satpute, André Greiner-Petter, Noah Gießing +4

Cosmodoit: A Python Package for Adaptive, Efficient Pipelining of Feature Extraction from Performed Music

Cosmodoit is a Python package that streamlines feature extraction from performed music by integrating various algorithms into an efficient, modular pipeline.

2605.03541May 5, 2026Corentin Guichaoua, Daniel Bedoya, Elaine Chew

SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation

SURE-RAG improves Retrieval-Augmented Generation by verifying evidence sufficiency, reducing unsafe answers through a transparent aggregation protocol.

2605.03534May 5, 2026Jingxi Qiu, Zeyu Han, Cheng Huang

Revisiting General Map Search via Generative Point-of-Interest Retrieval

GenPOI is a generative framework using LLMs to improve map search by handling underspecified queries through spatial-aware POI retrieval.

2605.03397May 5, 2026Dong Chen, Shuai Zheng, Haoyang Shao +5

RAG over Thinking Traces Can Improve Reasoning Tasks

This paper shows that using "thinking traces" as a retrieval corpus significantly enhances RAG performance on complex reasoning tasks like math and code.

2605.03344May 5, 2026Negar Arabzadeh, Wenjie Ma, Sewon Min +1

Beyond Similarity Search: A Unified Data Layer for Production RAG Systems

This paper proposes a unified PostgreSQL-based data layer for RAG systems, significantly improving reliability, performance, and security.

2605.03275May 5, 2026Venkata Krishna Prasanth Budigi, Siri Chandana Sirigiri

AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion

AlbumFill is a training-free framework that retrieves identity-consistent references from personal albums for personalized image completion.

2605.02892May 4, 2026Yu-Ju Tsai, Brian Price, Qing Liu +5

Multi-Axis Speech Similarity via Factor-Partitioned Embeddings

This paper introduces factor-partitioned embeddings to disentangle speech attributes like content and speaker identity, enabling multi-axis similarity for improved retrieval.

2605.02804May 4, 2026Jim O'Regan, Jens Edlund

Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study

This paper systematically compares five retrieval strategies for biomedical RAG, finding Cross-Encoder Reranking performs best.

2605.02520May 4, 2026Devi Prasad Bal, Subhashree Puhan

From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model

HEP-CoPilot is a retrieval-augmented multi-agent AI framework that unifies diverse high-energy physics data to accelerate BSM search interpretation.

2605.02491May 4, 2026Altan Cakir, Ayca Yerlikaya

GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing

GRAIL is a novel framework for real-time agent discovery, achieving sub-400ms latency and high accuracy using SLMs and fine-grained matching.

2605.02489May 4, 2026Jinliang Xu

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

FitText introduces a training-free framework that dynamically evolves agent tool retrieval by generating and refining pseudo-tool descriptions using memetic retrieval.

2605.02411May 4, 2026Kyle Zheng, Han Zhang, Renliang Sun +2

Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval

This paper introduces FiNE-Patents, a new dataset and LLM-based approach for fine-grained patent novelty prediction via passage retrieval.

2605.02392May 4, 2026Valentin Knappich, Anna Hätty, Simon Razniewski +1

Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems

This paper proposes a conceptual framework for designing fair multi-agent personalization systems that balance competing stakeholder objectives using LLM agents.

2605.02379May 4, 2026Andrea Forster, Peter Müllner, Denis Helic +2
PreviousPage 5 of 19Next

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.