50 articles mentioning context-1
arXiv:2610.27298v1 Announce Type: cross Abstract: Class-Incremental Learning (CIL) aims to learn new classes continuously without forgetting the previously learned ones. Recent works in CIL have significantly advanced across various modalities; however, at the intersection of audio-visual modality,
arXiv:2610.27301v1 Announce Type: cross Abstract: Language-model agents compact their context for the question at hand, but the compacted context must also serve questions that come later. We evaluate compaction on these later questions, using four corpora that annotate the evidence of several quest
arXiv:2610.28325v1 Announce Type: new Abstract: Factual sycophancy, a language model's deference to a user's false beliefs, is usually understood as a bid for the user's approval at the expense of truthfulness. We argue that this framing over-emphasizes the user and propose viewing sycophancy as a f
arXiv:2610.27347v1 Announce Type: new Abstract: Checking whether a text complies with a body of law is slow when done by hand and fragile when done with keyword rules. This paper presents ComplianceAgent, the legal compliance sub-agent of COMPASS, a multi-agent framework that evaluates texts along f
arXiv:2605.30251v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the sam
arXiv:2610.27407v1 Announce Type: new Abstract: Deception detection typically considers messages in isolation. Previous works in claim verification and role detection have displayed that additional information such as gameplay history is crucial to successful predictions. In this work, we demonstrat
arXiv:2610.27577v1 Announce Type: new Abstract: With increasing autonomy, Large Language Models (LLMs) may engage in deceptive behaviors, such as scheming to pursue misaligned goals or sandbagging to escape oversight. Monitoring outputs alone is insufficient, as models can produce seemingly benign r
arXiv:2610.27569v1 Announce Type: new Abstract: Tabular foundation models (TFMs) pretrain a transformer on large-scale synthetic priors so that a single forward pass yields zero-shot tabular prediction. TabICLv2 samples the class count of its classification prior during pretraining, and the prevaili
arXiv:2610.27986v1 Announce Type: cross Abstract: Long-horizon video generation requires retaining an ever-expanding history, but conditioning on its growing token sequence is costly. Existing methods restrict or compress historical context, potentially losing information needed for future generatio
arXiv:2610.27142v1 Announce Type: cross Abstract: Data selection plays a central role in modern large language model training, as the quality of training data strongly influences downstream performance. A common approach is to curate a development set that encodes the desired skills (e.g., reasoning
arXiv:2610.27583v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) predict multiple token positions per forward pass, yet block-wise decoders serialize generation and repeatedly recompute stable predictions. We attribute this inefficiency to coupling a prediction's readiness for
arXiv:2606.23687v3 Announce Type: replace Abstract: Large language models (LLMs) are typically pretrained on short sequences and then extended to work on longer sequences with additional training. However, such LLMs still struggle to further generalize to very long sequences. We propose Randomized Y
arXiv:2610.28364v1 Announce Type: cross Abstract: Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-para
arXiv:2603.26246v2 Announce Type: replace-cross Abstract: Standard LLM-based speech recognition systems process utterances in isolation, limiting their ability to leverage conversational context. Here we study whether multimodal context from prior turns improves LLM-based ASR and how to represent th
arXiv:2610.28483v1 Announce Type: new Abstract: Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive Architectures (JEPAs) offer a natural framework by modeling transitions directly in latent space rathe
arXiv:2610.26951v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it cannot anticipate which passages a question requires and d
arXiv:2610.27400v1 Announce Type: new Abstract: Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that anticipates user needs without explicit requests. However, existing proactive agents primarily address immediate needs, while many everyday situatio
arXiv:2610.26986v1 Announce Type: new Abstract: Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A reliable system must therefore exploit a relevant candidate without allowing unsu
arXiv:2601.16400v2 Announce Type: replace Abstract: Real-world visual question answering (VQA) may be context-dependent: an image-question pair could be under-specified, such that the correct answer depends on external information that is not observable in the image. In such cases, directly answerin
arXiv:2610.22897v1 Announce Type: new Abstract: Long-horizon agents learn from failure, but the value of a failure record can change as execution progresses. We study when retaining, compressing, or removing the same history block improves subsequent execution relative to full-history KEEP. We intro
arXiv:2610.22525v1 Announce Type: new Abstract: This paper describes team Alkhder's submission to Subtask 1 of the AlexandriaX-2026 shared task, which asks systems to translate English dialogue turns into thirteen Arabic dialects. We fine-tune NileChat-3B-Base with QLoRA on the Alexandria parallel d
arXiv:2610.23302v1 Announce Type: cross Abstract: Spatial context prediction requires visual grounding and spatial reasoning to identify vacant regions relative to objects in a scene. Spatial relationships and physical constraints remain challenging for large vision-language models (VLMs). Recursive
arXiv:2610.20865v1 Announce Type: new Abstract: Speculative decoding pairs a cheap drafter with parallel verification against the target. At ultra-long context it stops paying, because a drafter that attends over the full prefix inherits the target's context-dependent cost, so the speedup it was mea
arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and interactions among agents. Recent work has shifted agent safety guardrails from post-hoc trajectory-level
arXiv:2610.22167v1 Announce Type: new Abstract: Understanding a conversation requires connecting what is said to the speakers' relationships, expectations, and earlier exchanges. Prior work shows that supplying relevant context can improve models' social judgments, but much of this information may a
arXiv:2510.26309v2 Announce Type: replace Abstract: Regulatory compliance is an important requirement in many industrial and administrative settings. Yet compliance assessment remains difficult because regulatory requirements are distributed across structured documents and may depend on hierarchy, d
arXiv:2610.22273v1 Announce Type: cross Abstract: Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structure
arXiv:2604.25132v2 Announce Type: replace Abstract: Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI), which measur
arXiv:2610.21149v1 Announce Type: new Abstract: Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, existing methods filter demonstrations by observation, assuming a rationale is high-quality if it leads
arXiv:2610.20633v1 Announce Type: new Abstract: Long-horizon failures of language models are usually measured as end-task success or as a horizon length. We instead score, step by step, three components of a 400-step ledger task in which every step is easy in isolation and the model's own answers ar
arXiv:2606.17688v2 Announce Type: replace Abstract: Recent work has shown that LLMs overrepresent dominant cultures, particularly Western ones, while marginalizing others. We investigate whether this affects models' ability to generate culturally adapted responses by evaluating their use of local me
arXiv:2610.21362v1 Announce Type: cross Abstract: Robotic manipulation often requires remembering interactions that are no longer visible. We introduce Latent Transition Memory (LTM), which stores history as compact latent transitions between consecutive observations. Instantiated on $\pi_{0.5}$ as
arXiv:2610.20138v2 Announce Type: replace Abstract: Batch black-box optimization is important for expensive systems where many candidates can be evaluated in parallel, yet only a few rounds of evaluation are affordable. In this regime, effective batch construction must identify multiple promising re
arXiv:2610.21427v1 Announce Type: new Abstract: Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path: privileged information extracted from experience is provided to a teacher, whos
arXiv:2508.10068v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has advanced repository-level code completion by retrieving external code snippets, API documentation, or type definitions to expand the model's contextual awareness. However, under the finite token budget
arXiv:2610.20959v1 Announce Type: cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success depends on context. Three context-engineering techniques (CETs) help by shaping it: semant
arXiv:2610.17867v3 Announce Type: replace-cross Abstract: Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapting existing models to unseen datasets requires tens of thousands of examples. He
arXiv:2610.21736v1 Announce Type: new Abstract: Multi-objective optimization involves diverse preferences over conflicting objectives. Rather than returning a finite set of trade-off solutions, preference-conditioned Pareto set learning seeks to map a specified preference directly to a corresponding
arXiv:2610.21165v1 Announce Type: new Abstract: Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window does not remove the computational, storage, and information-selection pressures incurred at inference t
arXiv:2602.04212v3 Announce Type: replace-cross Abstract: Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its b
arXiv:2610.14913v1 Announce Type: new Abstract: Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training of large language models (LLMs), where tasks are commonly structured as Markov decision processes or
arXiv:2604.22560v2 Announce Type: replace-cross Abstract: Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present
arXiv:2610.20399v1 Announce Type: new Abstract: Context can improve large language model performance, but these gains may be lost after context removal. Inspired by biological systems consolidation, we formulate Memory Consolidation (MC) as internalizing these gains while preserving non-target capab
arXiv:2610.15509v1 Announce Type: cross Abstract: KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study \emph{zero-prefill cross-model context handoff}: translating a sender cach
arXiv:2608.11242v2 Announce Type: replace-cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We study Side Constraints (SCs), user-issued instructions such as "do not delete any emails until I confirm," that constrain an LLM's beha
arXiv:2506.13182v4 Announce Type: replace-cross Abstract: [...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general software bugs. Unfortunately, the effectiveness of these advanced techniques in the co
arXiv:2610.19552v1 Announce Type: new Abstract: Foundation models for dynamical systems can forecast unseen partial differential equations (PDEs), ordinary differential equations (ODEs), and time series during inference. However, it remains an open question whether these foundation models truly lear
arXiv:2610.20418v1 Announce Type: new Abstract: Tabular foundation models enable in-context learning by predicting unseen observations from a labeled support table without task-specific parameter updates. Despite recent advances, most existing approaches rely on dense architectures that apply the sa
arXiv:2610.10787v2 Announce Type: replace-cross Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and d
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history that still shapes the model's computation may change later actions, while retaining everything defea