Search: “context”

'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capability, but the harness determines tools, permissions and behavio

Does your context compactor actually save anything? If you built or tuned one, this one is worth your time. (bookmark it) Task completion is the standard way to validate compression, and it hides the

arXiv:2608.12724v1 Announce Type: new Abstract: Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance

Qwen 3.8-Max is live on Modal, with the full 1M context window and a custom DFlash speculator under the hood. Love seeing our launch partner Modal go all in from Day 0!⚡️ 2.4T parameters. 1M context.

arXiv:2608.11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instruction

arXiv:2608.10021v1 Announce Type: new Abstract: Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitati

arXiv:2608.06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary e

arXiv:2607.17142v3 Announce Type: replace-cross Abstract: Prior case retrieval (PCR) aims to identify the precedent cases relevant to the facts of a query case. Incoming citation context, the text wit

arXiv:2608.00528v1 Announce Type: new Abstract: The growth of context window lengths in Large Language Models (LLMs) significantly enhances their long-context capabilities but incurs prohibitive memor

arXiv:2608.02560v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache th

arXiv:2607.28642v1 Announce Type: new Abstract: Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error an

arXiv:2607.27637v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or sh

arXiv:2607.25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window. Existing

arXiv:2607.24882v1 Announce Type: cross Abstract: Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acqu

arXiv:2509.21028v4 Announce Type: replace Abstract: We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (

arXiv:2607.13220v1 Announce Type: new Abstract: Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, o

arXiv:2607.12963v1 Announce Type: new Abstract: As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by lo

arXiv:2607.06160v1 Announce Type: cross Abstract: Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs

arXiv:2607.02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense atte

arXiv:2607.00428v1 Announce Type: new Abstract: CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions

arXiv:2606.31474v1 Announce Type: new Abstract: Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak thro

arXiv:2501.14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety ben

arXiv:2606.22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show t

arXiv:2606.26105v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due t

arXiv:2606.24370v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have

Enterprise artificial intelligence context startup Jedify Inc. today announced that it has raised 24 million in new funding to build what it calls context graphs that give AI agents the business knowl

MTP (Multi-Token Prediction) doubled generation speed but provided only ~3% total latency reduction at 64k context length on an RTX 3090 GPU. The limited overall benefit at large context sizes suggest

arXiv:2606.09090v1 Announce Type: cross Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrule

arXiv:2601.06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also kn

arXiv:2512.14391v3 Announce Type: replace-cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextu

arXiv:2507.16003v4 Announce Type: replace Abstract: One of the most striking features of Large Language Models (LLMs) is their ability to learn in-context. Namely at inference time an LLM is able to l

arXiv:2602.23197v2 Announce Type: replace Abstract: Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrati

arXiv:2605.28079v1 Announce Type: new Abstract: Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task f

arXiv:2605.27774v1 Announce Type: new Abstract: In-context learning -- performing tasks based on examples given in the prompt -- is an important capability that has emerged in large language models an

arXiv:2605.27980v1 Announce Type: cross Abstract: The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extend

arXiv:2605.27254v1 Announce Type: cross Abstract: Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context sele

arXiv:2605.23296v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based su

arXiv:2603.11673v2 Announce Type: replace Abstract: Many physical systems exhibit a low-dimensional structure that varies with external parameters: link lengths in a robot, forcing constants in a flui

arXiv:2605.19577v1 Announce Type: new Abstract: We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR

arXiv:2605.14362v1 Announce Type: cross Abstract: Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models deg

Today we release Lighthouse Attention, a selection-based hierarchical attention for long-context pre-training that delivers a 1.4-1.7× wall-clock speedup at 98K context. It runs the same forward+backw

arXiv:2605.14478v1 Announce Type: cross Abstract: Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Ob

arXiv:2605.13485v1 Announce Type: new Abstract: Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representation

arXiv:2605.13511v1 Announce Type: cross Abstract: In-context learning (ICL) adapts large language models (LLMs) to new tasks by conditioning on demonstrations in the prompt without parameter updates.

arXiv:2605.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabul

arXiv:2605.12227v1 Announce Type: new Abstract: Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. E