Search: “context”

arXiv:2606.06443v1 Announce Type: new Abstract: Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it rema

arXiv:2606.05134v1 Announce Type: new Abstract: Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understandin

arXiv:2606.04109v1 Announce Type: new Abstract: Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but th

arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accu

Managed Deep Agents keeps the project shape you already know: ↳ AGENTS.md, skills/, subagents/, + tools.json Context Hub gives your agent a managed place to retain and update this context across sessi

arXiv:2510.02060v2 Announce Type: replace Abstract: In tabular anomaly detection (AD), textual semantics often carry critical signals, as the definition of an anomaly is closely tied to domain-specifi

arXiv:2510.24606v2 Announce Type: replace Abstract: The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is of

arXiv:2605.30274v1 Announce Type: cross Abstract: Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that

arXiv:2510.06182v2 Announce Type: replace Abstract: A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might repre

arXiv:2605.28705v1 Announce Type: new Abstract: In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassi

arXiv:2605.26902v1 Announce Type: cross Abstract: Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansi

arXiv:2605.26177v1 Announce Type: cross Abstract: Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on e

arXiv:2605.24410v1 Announce Type: new Abstract: Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning

arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cos

arXiv:2605.22262v1 Announce Type: cross Abstract: Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, t

arXiv:2605.22641v1 Announce Type: new Abstract: Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions betwe

arXiv:2508.09001v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, i

arXiv:2605.18979v1 Announce Type: new Abstract: We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) w

arXiv:2605.18512v1 Announce Type: new Abstract: In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possibl

arXiv:2605.18071v1 Announce Type: new Abstract: Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the ful

arXiv:2605.15505v1 Announce Type: new Abstract: In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication

arXiv:2605.12471v1 Announce Type: cross Abstract: We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold o

arXiv:2605.10642v1 Announce Type: new Abstract: Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that i

arXiv:2605.09009v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains

arXiv:2605.09649v1 Announce Type: new Abstract: The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction m

arXiv:2510.20797v2 Announce Type: replace-cross Abstract: Context compression reduces Transformer inference costs by replacing lengthy inputs with shorter pre-computed representations. It carries sign

arXiv:2605.10936v1 Announce Type: new Abstract: As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the

arXiv:2605.10466v1 Announce Type: new Abstract: Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the

arXiv:2605.10828v1 Announce Type: new Abstract: As large language models are increasingly deployed in retrieval-augmented generation and agentic systems that accumulate extensive context, understandin

arXiv:2605.07333v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) studies agents that, after pretraining, adapt to new tasks by conditioning on additional context without parame

This is harder to build than it looks. Preserving full conversational context while swapping underlying model providers mid-flight is a surprisingly deep systems problem. Most tools drop state or forc

arXiv:2605.04304v1 Announce Type: cross Abstract: Advanced chart question answering requires both precise perception of small visual elements and multi-step reasoning across several subplots. While ex

arXiv:2605.04569v1 Announce Type: new Abstract: Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottle

arXiv:2605.04116v1 Announce Type: cross Abstract: We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be

arXiv:2605.01372v1 Announce Type: new Abstract: Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively en

Last week we announced DeepSeek-V4. Today we’re sharing a closer look at DeepSeek-V4 Pro on Together AI: 512K context, controllable reasoning modes, and cached-input pricing for long-context workloads

A version of this article originally appeared on X. Every agent harness runs into the same limit: the context window is too small for everything the model might want to remember.... The post Context m

arXiv:2604.22161v1 Announce Type: new Abstract: We study the K-armed logistic bandit problem, where at each round, the agent observes K feature vectors associated with K actions. Existing approaches t

arXiv:2510.04548v2 Announce Type: replace-cross Abstract: In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It

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 finit

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

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-spe

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

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, a

arXiv:2502.13637v2 Announce Type: replace Abstract: Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action with

arXiv:2603.15250v2 Announce Type: replace Abstract: Symbolic regression aims to replace black-box predictors with concise analytical expressions that can be inspected and validated in scientific machi