Knowledge catalogue
arXiv:2610.06679v1 Announce Type: new Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditi
arXiv:2610.06651v1 Announce Type: new Abstract: Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environm
arXiv:2609.00759v1 Announce Type: new Abstract: Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output sc
arXiv:2605.15721v1 Announce Type: new Abstract: Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existin
arXiv:2606.06203v1 Announce Type: new Abstract: Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study le
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)
arXiv:2604.01601v2 Announce Type: replace Abstract: In-context fine-tuning (IC-Train), training an LLM with labeled examples in-context, is increasingly used in place of standard fine-tuning for domai
arXiv:2609.33166v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) enables large language model agents to adapt to new environments using their interaction history without updati
arXiv:2609.34781v1 Announce Type: new Abstract: Vision-language models (VLMs) can read text in natural scenes, but their predictions may be influenced by the surrounding context. When the printed text
arXiv:2604.16686v1 Announce Type: new Abstract: Large language models (LLMs) can answer questions and summarize documents when conditioned on external contexts (e.g., retrieved evidence), yet context
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,
arXiv:2604.17535v1 Announce Type: new Abstract: Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-traini
arXiv:2608.27756v1 Announce Type: new Abstract: Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olym
arXiv:2608.05141v1 Announce Type: new Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon
arXiv:2605.13831v1 Announce Type: new Abstract: Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-do
arXiv:2511.03475v4 Announce Type: replace Abstract: AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples
arXiv:2604.14339v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation a
arXiv:2602.22175v2 Announce Type: replace Abstract: Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long c
arXiv:2603.18446v2 Announce Type: replace Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selectio
arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that th
arXiv:2606.30005v1 Announce Type: new Abstract: Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management age
arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in
arXiv:2604.27660v1 Announce Type: new Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learn
arXiv:2604.07121v1 Announce Type: cross Abstract: In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence
arXiv:2508.13993v2 Announce Type: replace Abstract: Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reason
arXiv:2609.12686v1 Announce Type: cross Abstract: Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increas
arXiv:2505.17315v2 Announce Type: replace Abstract: Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this
arXiv:2505.19293v2 Announce Type: replace-cross Abstract: Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effort
arXiv:2510.02629v3 Announce Type: replace Abstract: Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, r
arXiv:2604.23371v1 Announce Type: new Abstract: This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's
arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte
arXiv:2609.35831v1 Announce Type: new Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented g
arXiv:2609.37725v1 Announce Type: new Abstract: We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file
arXiv:2607.23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context co
arXiv:2609.27603v1 Announce Type: cross Abstract: In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: t
arXiv:2609.26976v1 Announce Type: new Abstract: Learned context planning selects evidence atoms before an answer model reasons over them. We test whether this learned selection improves long-context m
arXiv:2609.05955v1 Announce Type: new Abstract: Tabular foundation models have become powerful graph learners. Systems such as G2T-FM and GraphPFN encode each node as a feature row and make prediction
arXiv:2609.05761v1 Announce Type: new Abstract: Visual geolocation benchmarks typically ask a model where an image was captured without accounting for the location context that users often provide. We
arXiv:2606.11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so th
arXiv:2610.07894v1 Announce Type: new Abstract: Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is insuf
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data
arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with st
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an en
arXiv:2511.20011v3 Announce Type: replace-cross Abstract: Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. Howev
arXiv:2608.03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant infor
arXiv:2607.03660v1 Announce Type: cross Abstract: Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt.
arXiv:2507.04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) withou
arXiv:2606.01336v1 Announce Type: new Abstract: As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a
arXiv:2605.17304v1 Announce Type: cross Abstract: LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool res
arXiv:2502.14644v5 Announce Type: replace Abstract: Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine
arXiv:2604.09494v1 Announce Type: cross Abstract: We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which ide
arXiv:2507.06415v3 Announce Type: replace Abstract: Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Param
arXiv:2608.05237v1 Announce Type: cross Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the curren
arXiv:2605.10544v1 Announce Type: new Abstract: Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking,
arXiv:2512.21439v2 Announce Type: replace-cross Abstract: A key question in current AI alignment research is how to make AI algorithms learn moral values. Because human morality is highly context-depe
arXiv:2609.22101v1 Announce Type: new Abstract: Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusab
arXiv:2608.15536v1 Announce Type: new Abstract: In value-based argumentation, an audience's ordering of values decides which attacks succeed as defeats. In many settings the deciding factor is not the
arXiv:2608.12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This
arXiv:2610.11152v1 Announce Type: cross Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often desc