48 articles mentioning context-1
arXiv:2505.11336v4 Announce Type: replace Abstract: Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text generation a
arXiv:2601.11044v4 Announce Type: replace Abstract: Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture long-horizon
arXiv:2604.16395v2 Announce Type: replace-cross Abstract: Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming
arXiv:2604.21018v1 Announce Type: new Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute allocation framework
arXiv:2508.07117v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inhe
arXiv:2604.20874v1 Announce Type: cross Abstract: Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these constraints as axiom
arXiv:2604.20911v1 Announce Type: cross Abstract: LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential disclosure, data exfiltration, and unauthorized output) that safety evaluations assume hold throughout
arXiv:2511.07752v3 Announce Type: replace Abstract: Contextual predictability shapes how we choose and encode words in production. The effects of a word's predictability given preceding or past context are generally well-understood in both production and comprehension, but studies of naturalistic pr
arXiv:2603.12451v3 Announce Type: replace Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal mode
arXiv:2603.21373v2 Announce Type: replace Abstract: In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Among other factors, performance is often highly sensitive to the ordering of the examples. However, exhaustiv
arXiv:2509.21361v2 Announce Type: replace-cross Abstract: Large language model (LLM) providers boast big numbers for maximum context window sizes. To test the real world use of context windows, we 1) define a concept of maximum effective context window, 2) formulate a testing method of a context win
arXiv:2509.21275v3 Announce Type: replace-cross Abstract: Long context training is crucial for LLM's context extension. Existing schemes, such as sequence parallelism, incur substantial communication overhead. Pipeline parallelism (PP) reduces this cost, but its effectiveness hinges on partitioning
arXiv:2604.20824v1 Announce Type: new Abstract: The central problem in biomedical imaging are batch effects: systematic technical variations unrelated to the biological signal of interest. These batch effects critically undermine experimental reproducibility and are the primary cause of failure of d
arXiv:2603.18740v2 Announce Type: replace-cross Abstract: Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive assistants to autonomous agents in CI/CD pipelines. In this paper, we study how
arXiv:2604.21308v1 Announce Type: cross Abstract: Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce CI-Work, a Conte
arXiv:2601.06606v2 Announce Type: replace Abstract: We demonstrate CEDAR, an application for automating data science (DS) tasks with an agentic setup. Solving DS problems with LLMs is an underexplored area that has immense market value. The challenges are manifold: task complexities, data sizes, com
arXiv:2604.19769v1 Announce Type: cross Abstract: Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV states as equ
arXiv:2604.21814v1 Announce Type: cross Abstract: Capsule endoscopy (CE) enables non-invasive gastrointestinal screening, but current CE research remains largely limited to frame-level classification and detection, leaving video-level analysis underexplored. To bridge this gap, we introduce and form
arXiv:2506.19977v2 Announce Type: replace Abstract: Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy retrieval-augmented generation. We propose a novel framework that formulates context
arXiv:2603.26692v3 Announce Type: replace-cross Abstract: We introduce a new notion, that of a contextuality profile of a system of random variables. Rather than characterizing a system's contextuality by a single number, its overall degree of contextuality, we show how it can be characterized by a
arXiv:2604.20348v1 Announce Type: cross Abstract: Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf, text-only LLMs to predict robot actions without any task-specific training while preserving their
arXiv:2509.25844v3 Announce Type: replace Abstract: When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural language explanations can signal which model predictions are reliable. How
arXiv:2604.19771v1 Announce Type: cross Abstract: LLM agents lack persistent memory, causing conversations to reset each session and preventing personalization over time. We present Lyzr Cognis, a unified memory architecture for conversational AI agents that addresses this limitation through a multi
arXiv:2604.20267v1 Announce Type: cross Abstract: Audio carries richer information than text, including emotion, speaker traits, and environmental context, while also enabling lower-latency processing compared to speech-to-text pipelines. However, recent multimodal information retrieval research has
arXiv:2604.20216v1 Announce Type: new Abstract: Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empirical-quantile supervision, where each input is paired with multiple observ
arXiv:2604.19351v2 Announce Type: replace Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they often s
arXiv:2601.12078v2 Announce Type: replace Abstract: Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alternative to fine-tuning by conditioning LLMs on user history records
arXiv:2601.11913v2 Announce Type: replace-cross Abstract: Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often enco
arXiv:2602.12735v2 Announce Type: replace-cross Abstract: Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on linear interaction histories, which struggle to han
arXiv:2604.18912v1 Announce Type: new Abstract: Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achieved remarkable success in this setting, growing attention has recently turned to context-specific opt
arXiv:2604.18758v1 Announce Type: new Abstract: Low-resource machine translation requires methods that differ from those used for high-resource languages. This paper proposes a novel in-context learning approach to support low-resource machine translation of the Coptic language to English, with synt
arXiv:2511.11793v3 Announce Type: replace Abstract: We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction s
arXiv:2604.19639v1 Announce Type: cross Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner must optimize a task objective using only feasibility samples from a black-box Simulator, conditioned
arXiv:2601.21092v2 Announce Type: replace Abstract: Planning effective interventions in biological systems requires treatment-effect models that adapt to unseen biological contexts by identifying their specific underlying mechanisms. Yet single-cell perturbation datasets span only a handful of biolo
arXiv:2603.13779v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform in industrial anomaly detection (IAD). This is because MLLMs trained mostly on general web data diff
arXiv:2512.16059v2 Announce Type: replace-cross Abstract: In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information, reli
arXiv:2604.19572v1 Announce Type: new Abstract: As model capabilities advance, research has increasingly shifted toward long-horizon, multi-turn terminal-centric agentic tasks, where raw environment feedback is often preserved in the interaction history to support future decisions. However, repeated
arXiv:2508.01959v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is o
arXiv:2604.19021v1 Announce Type: new Abstract: Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have demonstrated that the delta rule
arXiv:2604.18398v2 Announce Type: replace-cross Abstract: Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment ins
arXiv:2603.22608v2 Announce Type: replace Abstract: Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the sentiment
arXiv:2510.11288v4 Announce Type: replace Abstract: Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to finetuning and activation steering, leaving out in-context learning (
arXiv:2601.15220v2 Announce Type: replace Abstract: We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for helpfulness, ex
arXiv:2604.15547v1 Announce Type: cross Abstract: The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the analytical
arXiv:2509.21623v2 Announce Type: replace-cross Abstract: The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache required for autoregressive generation. This bottleneck is substantial; for instance, a Llama-3.1-8B
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 feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key limitations: the f
arXiv:2604.15343v1 Announce Type: cross Abstract: We report a detailed autoethnographic case study of a single-subject who deliberately constructed and operated a multi-modal prompt-engineering system (System A) designed to externalize cognitive self-regulation onto a large language model (LLM). Wit