Daily edition · Information Retrieval
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
34 articles · 4 sources · 34 papers ·
Top topics: AI Research · AI · Information Retrieval
arXiv:2609.19759v1 Announce Type: new Abstract: The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent…
arXiv:2609.19827v1 Announce Type: new Abstract: With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically…
arXiv:2602.17099v2 Announce Type: replace-cross Abstract: Approximate k Nearest Neighbor (AKNN) search in high-dimensional space is a foundational problem in vector databases with widespread applications. Among the…
arXiv:2609.19831v1 Announce Type: new Abstract: In this reproducibility study, we investigate the transparency and scrutability of recommender systems enhanced by incorporating generated natural-language user profiles…
arXiv:2608.25245v2 Announce Type: replace Abstract: LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concepts that presuppose answer-side document knowledge, violating the…
arXiv:2609.19656v1 Announce Type: new Abstract: Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that…
arXiv:2609.19787v1 Announce Type: new Abstract: We describe our 10th-place solution to the KDD Cup 2026 Tencent UniRec Challenge, industrial click-to-conversion (CVR) prediction over 34.82M records, and we ask which…
arXiv:2606.01670v3 Announce Type: replace Abstract: Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs). Owing…
arXiv:2609.19615v1 Announce Type: cross Abstract: Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business insights remains a…
arXiv:2609.02062v2 Announce Type: replace Abstract: Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's semantic ID (SID), holds great promise for Location-Based Services, where…
arXiv:2609.20131v1 Announce Type: new Abstract: Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single…
arXiv:2609.19151v1 Announce Type: cross Abstract: Generative AI (GenAI) applications have achieved rapid consumer adoption, yet little large-scale research examines user-perceived quality, trust, and adoption barriers.…
arXiv:2609.19483v1 Announce Type: cross Abstract: Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-encoders. We ask…
arXiv:2609.19680v1 Announce Type: cross Abstract: Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed…
arXiv:2609.20563v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown strong potential for producing context-rich text embeddings for retrieval. Most existing methods either treat embedding…
arXiv:2609.19585v1 Announce Type: cross Abstract: In mental health care, reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of biological,…
arXiv:2506.17277v2 Announce Type: replace Abstract: The retrieval stage of retrieval-augmented generation (RAG) for scientific question answering depends on how documents are segmented and how chunks are represented in…
arXiv:2609.06027v2 Announce Type: replace-cross Abstract: Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. Existing…
arXiv:2609.20303v1 Announce Type: cross Abstract: Classical philosophical corpora pose three compounding challenges for language resources: they exist in several languages without parallel alignment, their vocabulary is…
arXiv:2609.19244v1 Announce Type: cross Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the first study of Web…
Showing 1 day · 34 items available
