Topic - Edition
arXiv:2610.13810v1 Announce Type: new Abstract: Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add…
arXiv:2412.13844v2 Announce Type: replace Abstract: Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present the Controllable…
arXiv:2610.13314v1 Announce Type: new Abstract: Memory retrieval aims to identify evidence from stored records to answer a query. Stored records with different factual details may share topics, entities, or events. Such…
arXiv:2610.13296v1 Announce Type: new Abstract: High-precision retrieval over external knowledge bases is essential for LLM agents to operate effectively. However, existing Information Retrieval (IR) research primarily…
arXiv:2610.13889v1 Announce Type: cross Abstract: As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore…
arXiv:2610.12617v1 Announce Type: cross Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their…
arXiv:2605.09040v4 Announce Type: replace-cross Abstract: Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific…
arXiv:2610.13416v1 Announce Type: cross Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effective web access…
arXiv:2603.07233v3 Announce Type: replace-cross Abstract: Predicting transcriptional responses to genetic perturbations is fundamental to functional genomics and therapeutic discovery. Recent deep learning models have…
arXiv:2609.01642v2 Announce Type: replace Abstract: Effective skill identification is crucial for LLM agents to reuse task-solving experience for complex task execution, which however remains challenging as agents must…
arXiv:2609.29145v2 Announce Type: replace-cross Abstract: A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the…
arXiv:2610.13277v1 Announce Type: new Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare single-vector…
arXiv:2610.13128v1 Announce Type: cross Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents…
arXiv:2610.13648v1 Announce Type: new Abstract: Querying distributed data represented as Knowledge Graphs (KGs) via SPARQL remains a difficult task, requiring fluency in query syntax, endpoint specifications, and schema…
arXiv:2509.00303v5 Announce Type: replace-cross Abstract: In this work, we present the \texttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical implementations.…
arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after a decision.…
arXiv:2610.13948v1 Announce Type: cross Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist…
arXiv:2609.19844v2 Announce Type: replace-cross Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework…
Recently I created a Facebook scraper that can scrape profiles, posts, comments, reactions, groups, Marketplace and search engine. It's free and open source. It's lightweight, doesn't use a headless browser and doesn't…
