Knowledge catalogue
arXiv:2604.17935v1 Announce Type: new Abstract: The key-value (KV) cache is the dominant memory bottleneck during Transformer inference, yet little is known theoretically about how aggressively it can
arXiv:2604.16422v1 Announce Type: new Abstract: The injection of domain-specific knowledge is crucial for adapting language models (LMs) to specialized fields such as biomedicine. While most current a
arXiv:2604.17866v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallu
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
ReasoningBank is a memory framework that distills generalizable reasoning strategies from an agent's successful and failed experiences, which the agent retrieves at test time to inform interactions wh
arXiv:2510.15253v3 Announce Type: replace Abstract: Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines
arXiv:2505.21471v2 Announce Type: replace Abstract: With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large q
arXiv:2603.18361v2 Announce Type: replace Abstract: Conversational agents are required to respond to their users not only with high quality (i.e. commonsense bearing) responses, but also considering m
arXiv:2510.09671v2 Announce Type: replace Abstract: Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text p
arXiv:2508.11184v2 Announce Type: replace Abstract: Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify s
arXiv:2509.23714v2 Announce Type: replace Abstract: Multi-modal knowledge graph completion (MMKGC) aims to discover missing facts in multi-modal knowledge graphs (MMKGs) by leveraging both structural
arXiv:2604.15456v1 Announce Type: new Abstract: Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent d
arXiv:2604.15646v1 Announce Type: new Abstract: Clinicians exploring oncology trial repositories often need ad-hoc, multi-constraint queries over biomarkers, endpoints, interventions, and time, yet wr
arXiv:2604.15951v1 Announce Type: new Abstract: Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured d
arXiv:2604.15529v1 Announce Type: new Abstract: Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not inter
arXiv:2604.15727v1 Announce Type: new Abstract: Large language models exhibit systematic limitations in structured logical reasoning: they conflate hypothesis generation with verification, cannot dist
arXiv:2604.14779v1 Announce Type: cross Abstract: In continual visual question answering (VQA), existing Continual Learning (CL) methods are mostly built for symmetric, unimodal architectures. However
arXiv:2604.15069v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural message passing. In this work, we substitute
arXiv:2604.13041v1 Announce Type: cross Abstract: Table Structure Recognition (TSR) requires the logical reasoning ability of large language models (LLMs) to handle complex table layouts, but current
arXiv:2506.20083v4 Announce Type: replace Abstract: Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, com
arXiv:2402.01720v3 Announce Type: replace-cross Abstract: University students often spend a considerable amount of time seeking answers to common questions from administrators or teachers. This can be
arXiv:2604.13979v1 Announce Type: new Abstract: Open-world Question Answering (OW-QA) over knowledge graphs (KGs) aims to answer questions over incomplete or evolving KGs. Traditional KGQA assumes a c
arXiv:2505.17086v4 Announce Type: replace Abstract: Large Language Models (LLMs) equipped with modern Retrieval-Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to inte
arXiv:2604.12421v1 Announce Type: new Abstract: Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large l
arXiv:2601.11047v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations.
arXiv:2511.02627v2 Announce Type: replace Abstract: We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse com
arXiv:2510.03323v2 Announce Type: replace Abstract: Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving inform
arXiv:2604.12285v1 Announce Type: new Abstract: To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining
arXiv:2604.12748v1 Announce Type: new Abstract: Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (
arXiv:2604.11810v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number
arXiv:2604.12390v1 Announce Type: new Abstract: This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like st
arXiv:2604.12651v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) models perform well on link prediction but struggle with unseen entities, relations, and especially literals, limiting
arXiv:2604.12018v1 Announce Type: cross Abstract: Understanding abstract meanings is crucial for advanced language comprehension. Despite extensive research, abstract words remain challenging due to t
arXiv:2604.12766v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) typically relies on a flat retrieval paradigm that maps queries directly to static, isolated text segments. This ap
arXiv:2604.12867v1 Announce Type: new Abstract: As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this
arXiv:2511.09803v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factuality but retrieving for every query often hurts quality while inflating tokens and latency. We p
arXiv:2604.12890v1 Announce Type: cross Abstract: Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, mana
arXiv:2510.10182v2 Announce Type: replace-cross Abstract: Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamen
arXiv:2602.02007v3 Announce Type: replace-cross Abstract: Agent memory systems often adopt the standard Retrieval-Augmented Generation (RAG) pipeline, yet its underlying assumptions differ in this set
arXiv:2604.10973v1 Announce Type: new Abstract: Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both fr
arXiv:2604.10426v1 Announce Type: cross Abstract: Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While
arXiv:2601.04377v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowled
arXiv:2604.09666v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reason
arXiv:2604.10455v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled promising progress in diagnosis prediction from electronic health records (EHRs). However,
arXiv:2511.12968v2 Announce Type: replace Abstract: Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semant
arXiv:2604.11144v1 Announce Type: cross Abstract: Image clustering aims to group images in an unsupervised fashion. Traditional methods focus on knowledge from visual space, making it difficult to dis
Today, we're thrilled to announce that BigQuery Graph is now available in preview. With BigQuery Graph, we’ve built an easy-to-use, highly scalable graph analytics solution for data engineers, data an
arXiv:2510.01152v2 Announce Type: replace Abstract: LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper,
arXiv:2601.22361v2 Announce Type: replace-cross Abstract: Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial prog
arXiv:2604.11502v1 Announce Type: cross Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate th
arXiv:2603.23516v2 Announce Type: replace-cross Abstract: Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in
arXiv:2604.10087v1 Announce Type: new Abstract: We present EL-DRUIN, an ontological reasoning system for geopolitical intelligence analysis that combines formal ontology, finite semigroup algebra, and
arXiv:2604.10908v1 Announce Type: new Abstract: Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(A
arXiv:2604.11407v1 Announce Type: cross Abstract: We revisit retrieval-augmented generation (RAG) by embedding retrieval control directly into generation. Instead of treating retrieval as an external
Over 80% of enterprise data lives in unstructured form — PDFs, emails, reports, regulatory filings. Most of the time, such sources contain critical business information, yet they remain difficult to a
arXiv:2604.10734v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges
arXiv:2604.11557v1 Announce Type: new Abstract: Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However
arXiv:2604.05418v2 Announce Type: replace-cross Abstract: Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generatio
arXiv:2604.09251v1 Announce Type: new Abstract: Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these capabilities in isolation,
arXiv:2604.08728v1 Announce Type: new Abstract: Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and exis