Knowledge catalogue
arXiv:2605.13137v1 Announce Type: cross Abstract: Proving theorems in Lean 4 often requires identifying a scattered set of library lemmas whose joint use enables a concise proof -- a task we call glob
arXiv:2605.13534v1 Announce Type: new Abstract: Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often
arXiv:2511.13415v2 Announce Type: replace-cross Abstract: Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances
arXiv:2602.11162v2 Announce Type: replace Abstract: Recent studies have identified 'retrieval heads' in Large Language Models (LLMs) responsible for extracting information from input contexts. However
arXiv:2605.03534v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds answers in retrieved passages, but retrieval is not verification: a passage can be topical and still fail t
arXiv:2601.05254v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However,
arXiv:2604.00809v2 Announce Type: replace Abstract: Building on existing approaches, we revisit Human-in-the-Loop Object Retrieval, a task that consists of iteratively retrieving images containing obj
arXiv:2604.22759v1 Announce Type: cross Abstract: In community question answering (cQA) platforms like Stack Overflow, related question retrieval is recognized as a fundamental task that allows users
arXiv:2604.23783v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterativ
arXiv:2604.24623v1 Announce Type: new Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a str
arXiv:2604.20572v1 Announce Type: new Abstract: Online lifelong learning enables agents to accumulate experience across interactions and continually improve on long-horizon tasks. However, existing me
arXiv:2505.14984v2 Announce Type: replace Abstract: Open-Domain Table Question Answering (TQA) involves retrieving relevant tables from a large corpus to answer natural language queries. Traditional d
arXiv:2604.18509v1 Announce Type: new Abstract: Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when
arXiv:2505.17238v3 Announce Type: replace Abstract: Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent in
arXiv:2604.16351v1 Announce Type: cross Abstract: Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identit
arXiv:2604.12610v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. Howe
arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory do
arXiv:2610.22297v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it ca
arXiv:2610.15463v1 Announce Type: new Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly con
arXiv:2412.13844v2 Announce Type: replace-cross Abstract: Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present
arXiv:2610.13510v1 Announce Type: new Abstract: Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRI
arXiv:2610.08716v1 Announce Type: cross Abstract: Generative retrieval trains a language model to generate the identifier of a relevant document. Recent work replaces the autoregressive decoder with d
arXiv:2610.08098v1 Announce Type: cross Abstract: AI agents increasingly rely on modular third-party 'skills' that are dynamically selected by skill routers to execute complex tasks. While recent stud
arXiv:2610.01230v1 Announce Type: new Abstract: Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval off
arXiv:2510.13935v3 Announce Type: replace-cross Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which nee
arXiv:2608.03756v2 Announce Type: cross Abstract: A common task in legal Information Retrieval (IR) is to find relevant legal sources from case-law collections. While legal practice often requires pin
arXiv:2609.38530v1 Announce Type: new Abstract: Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window
arXiv:2609.36815v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotation
arXiv:2609.30889v1 Announce Type: new Abstract: Contact-rich assembly tasks such as peg-in-hole insertion remain difficult to learn from limited demonstrations. While retrieval-augmented imitation lea
arXiv:2609.30467v1 Announce Type: new Abstract: Retrieval-based factuality evaluation, where LLM-generated claims are verified against evidence from authoritative medical corpora, has become the domin
arXiv:2609.18248v1 Announce Type: cross Abstract: An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-n
arXiv:2609.15335v1 Announce Type: new Abstract: Multimodal retrieval integrates video, audio, subtitles, and text; however, recent geometric aggregators, such as Gramian volumes, hyperbolic volumes, a
arXiv:2609.08174v1 Announce Type: new Abstract: We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs ac
arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage a
arXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, moti
arXiv:2608.30130v1 Announce Type: cross Abstract: Retrieval-augmented language models can fail to respect negative constraints when the retriever supplies evidence about concepts the user explicitly e
arXiv:2608.28968v1 Announce Type: new Abstract: Semantic Search on LinkedIn must retrieve relevant profiles from a corpus of hundreds of millions in response to natural-language queries such as 'a fin
arXiv:2608.30606v1 Announce Type: cross Abstract: With the development of large language models (LLMs), generative retrieval is becoming increasingly important in e-commerce scenarios. Current mainstr
arXiv:2608.28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning:
arXiv:2608.26632v1 Announce Type: new Abstract: Gait recognition has achieved remarkable progress, yet existing methods remain confined to rigid visual matching and often overlook the potential of nat
arXiv:2604.03403v2 Announce Type: replace-cross Abstract: Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collect
arXiv:2608.23965v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also expose
arXiv:2608.18534v1 Announce Type: new Abstract: Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive
arXiv:2608.17171v1 Announce Type: new Abstract: Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generat
arXiv:2608.16071v1 Announce Type: new Abstract: Pseudo-query generation can alleviate the supervision bottleneck for agent skill retrieval, but existing document-level approaches typically leave the r
arXiv:2608.12129v1 Announce Type: new Abstract: While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementations
arXiv:2608.02880v1 Announce Type: cross Abstract: As lifelong learning agents accumulate lifelong growing skill banks, retrieving the correct skill becomes an increasingly important bottleneck. Most c
arXiv:2608.02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking informat
arXiv:2607.29440v1 Announce Type: new Abstract: Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions.
arXiv:2607.24748v1 Announce Type: cross Abstract: Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing t
arXiv:2607.22597v1 Announce Type: new Abstract: Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process
arXiv:2607.14561v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge
arXiv:2607.22584v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or cre
arXiv:2607.22639v1 Announce Type: new Abstract: Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via co
arXiv:2607.20291v1 Announce Type: new Abstract: Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictiv
arXiv:2607.06641v1 Announce Type: cross Abstract: Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hall
arXiv:2508.01389v3 Announce Type: replace Abstract: Person retrieval in surveillance videos often depends on attributes described by witnesses or operators. However, the most useful cues in practice a
arXiv:2606.28343v1 Announce Type: cross Abstract: Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis. This isolates interactio
arXiv:2512.00804v3 Announce Type: replace-cross Abstract: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. The
arXiv:2606.25237v1 Announce Type: cross Abstract: We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. Con