Search: “context”

arXiv:2604.08075v1 Announce Type: new Abstract: Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-ut

arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path

arXiv:2508.15813v2 Announce Type: replace-cross Abstract: A big issue in modern LLM applications is they tend to feed long context to LLM, which results in high inference cost and latency, and may exc

arXiv:2511.04707v2 Announce Type: replace-cross Abstract: Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks lik

arXiv:2512.11614v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic

arXiv:2608.02515v1 Announce Type: new Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retri

arXiv:2607.28979v1 Announce Type: new Abstract: Heterogeneous Large Language Model (LLM) systems increasingly rely on shared contexts, retrieved evidence, and multi-agent dialogue histories, yet their

arXiv:2604.19312v1 Announce Type: new Abstract: Neural processes are meta-learning models that map context sets to predictive distributions. While inspired by stochastic processes, NPs do not generall

arXiv:2604.08584v1 Announce Type: cross Abstract: Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the domi

arXiv:2610.20927v1 Announce Type: new Abstract: Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-la

arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Exi

arXiv:2610.08314v1 Announce Type: new Abstract: Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each

arXiv:2610.04518v1 Announce Type: new Abstract: Length generalization is the ability of sequential models to perform well on context lengths unseen during training. In this work, we show that the chal

arXiv:2610.06686v1 Announce Type: new Abstract: Long context inference with large language models becomes increasingly expensive as attention must operate over an ever growing KV cache. Page sparse at

arXiv:2511.09665v1 Announce Type: cross Abstract: Deep tabular modelling increasingly relies on in-context learning where, during inference, a model receives a set of (x,y) pairs as context and predic

arXiv:2609.10702v1 Announce Type: new Abstract: Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-hori

arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco

arXiv:2608.20397v1 Announce Type: new Abstract: Agentic large language models (LLMs) on the Model Context Protocol (MCP) re-encode verbose tool schemas every turn, so prefill - quadratic in sequence l

arXiv:2608.12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, howeve

arXiv:2608.01662v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrain

arXiv:2510.20535v2 Announce Type: replace Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Co

arXiv:2607.13314v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) generate predictions on structured data via in-context learning, without task-specific estimation. We ask whether TFM

arXiv:2607.12550v1 Announce Type: cross Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference. It grows with batch size, context length, and depth, and at lon

arXiv:2607.04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on.

arXiv:2606.24267v1 Announce Type: cross Abstract: While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode

arXiv:2604.22678v1 Announce Type: new Abstract: A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a lan

arXiv:2604.21100v1 Announce Type: new Abstract: To address the increasing long-context compute limitations of softmax attention, several subquadratic recurrent operators have been developed. This work

arXiv:2604.15180v1 Announce Type: cross Abstract: Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promisin

arXiv:2604.07815v1 Announce Type: new Abstract: Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse att

arXiv:2604.07737v1 Announce Type: new Abstract: While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when

arXiv:2610.20582v1 Announce Type: new Abstract: Long contexts enlarge key--value (KV) caches, increasing memory use and attention costs during generation. Compressing these caches must preserve inform

arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free re

arXiv:2610.05352v1 Announce Type: new Abstract: Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this succ

arXiv:2610.00820v1 Announce Type: cross Abstract: General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaini

arXiv:2609.39938v1 Announce Type: cross Abstract: Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, wherea

arXiv:2609.26779v1 Announce Type: cross Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context

arXiv:2609.03235v1 Announce Type: new Abstract: Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existin

arXiv:2609.02737v1 Announce Type: cross Abstract: Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If

arXiv:2609.02011v1 Announce Type: cross Abstract: Large language model question answering over power-grid models must respect a fixed context budget. We introduce seed-anchored graph rendering, a dete

arXiv:2608.17957v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts label

arXiv:2608.00902v1 Announce Type: new Abstract: LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV c

arXiv:2607.22562v1 Announce Type: new Abstract: Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning.

arXiv:2607.21692v1 Announce Type: cross Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input. These selectors are often trained

arXiv:2506.20699v2 Announce Type: replace Abstract: Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization. A system must also discover which

arXiv:2605.13687v1 Announce Type: cross Abstract: We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context

arXiv:2605.13188v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in settings where the available context is incomplete or degraded. We argue that an LLM generat