Knowledge catalogue
arXiv:2607.06720v1 Announce Type: new Abstract: Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise
arXiv:2607.05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/l
arXiv:2512.13956v4 Announce Type: replace-cross Abstract: Cloud-native systems have made operational work both more powerful and harder to automate: incidents unfold across microservices, logs and met
arXiv:2603.10174v2 Announce Type: replace Abstract: Autonomous underwater vehicles (AUVs) are increasingly used to survey coral reefs, yet efficiently locating specific coral species of interest remai
arXiv:2607.02575v1 Announce Type: cross Abstract: Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the suppor
Untied Ulysses is a memory-efficient technique for context parallelism that processes attention heads in chunks rather than sequences, reducing memory overhead during transformer inference and trainin
arXiv:2606.31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), achieve state-of-the-art performance on tabular tasks
Context engineering has its own track at the @aiDotEngineer World's Fair this year. 🎉 I've respected what @swyx and the @latentspacepod team have been building for years — and I'm pumped to be a part
arXiv:2606.30336v1 Announce Type: new Abstract: We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a
arXiv:2606.28876v1 Announce Type: new Abstract: Long-context language models often conflate two different goals: compressing history into an efficient state, and maintaining reliable long-term memory.
arXiv:2606.29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies,
arXiv:2606.27732v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) recover masked tokens in parallel, offering significant speedups over autoregressive (AR) generation. Howev
arXiv:2606.28050v1 Announce Type: cross Abstract: LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation. We test this in a controlled in-context QA s
arXiv:2603.26629v2 Announce Type: replace Abstract: Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typicall
arXiv:2606.28149v1 Announce Type: cross Abstract: In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding ma
arXiv:2606.26025v1 Announce Type: cross Abstract: Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoints or robot morphologies, because
arXiv:2606.25342v1 Announce Type: new Abstract: Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context
arXiv:2606.24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiti
arXiv:2606.24460v1 Announce Type: cross Abstract: Commercial large language models bill, scale latency, and budget context per token. Yet tokenizers assign more subword tokens to the same meaning in s
arXiv:2603.25857v2 Announce Type: replace Abstract: The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecula
arXiv:2606.12291v1 Announce Type: new Abstract: Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical ju
arXiv:2602.21788v2 Announce Type: replace-cross Abstract: Scaling long-context capabilities is crucial for Large Language Models (LLMs). However, real-world data contain a large number of sequences wi
arXiv:2606.07623v1 Announce Type: new Abstract: This paper develops a model-theoretic framework for verifying context-conditioned language-model behavior by replacing benchmark labels with finite sema
arXiv:2606.09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets acr
arXiv:2508.19239v2 Announce Type: replace Abstract: The rapid expansion of interconnected devices, autonomous systems, and AI applications has created severe fragmentation in adaptive transport system
arXiv:2606.06223v1 Announce Type: new Abstract: Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal mode
arXiv:2606.06337v1 Announce Type: new Abstract: Large language model (LLM) deployments for long-horizon tasks face a fundamental constraint: context windows are finite while productive work sessions a
arXiv:2606.06197v1 Announce Type: new Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs). However, they still face challenges in a
arXiv:2606.05182v1 Announce Type: new Abstract: Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered
arXiv:2606.03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain funda
arXiv:2606.01101v1 Announce Type: cross Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) processing ultra-long contexts. The Naive Bayes Cogni
arXiv:2605.30699v1 Announce Type: cross Abstract: This work proposes a context-aware middleware for medical workflow organization and efficiency improvement. In hospitals, laboratories and teleradiolo
arXiv:2605.31145v1 Announce Type: cross Abstract: In-context localization (ICL) seeks to localize a target object specified by a small set of support examples in a query image, operating on the fly wi
arXiv:2605.31584v1 Announce Type: cross Abstract: Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive di
arXiv:2504.06022v3 Announce Type: replace Abstract: Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditi
arXiv:2605.28889v1 Announce Type: cross Abstract: Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories
arXiv:2605.29675v1 Announce Type: cross Abstract: Collaborations with Generative AI often begin with a short prompt and end with an opaque output, leaving implicit who was involved, what task was bein
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-c
arXiv:2509.25582v3 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks w
arXiv:2605.28211v1 Announce Type: new Abstract: SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sens
arXiv:2601.20796v2 Announce Type: replace Abstract: Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do t
arXiv:2605.26525v1 Announce Type: cross Abstract: Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challeng
arXiv:2605.26165v1 Announce Type: cross Abstract: Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict: tool schemas consume the
arXiv:2605.25475v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows line
A full tour through RAG, document context, and AI agents - from 2023 to 2026 🌎🤖 @hexapode gave a comprehensive 90-min workshop at @aiDotEngineer Singapore last week that comprehensively traces through
arXiv:2601.11079v2 Announce Type: replace Abstract: This paper proposes the soft Bayesian context tree model (Soft-BCT), which is a novel BCT model for real-valued time series. The Soft-BCT considers
LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process long contexts, recover earlier information, and reason over many updates that cre
arXiv:2605.16591v1 Announce Type: cross Abstract: In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model
arXiv:2506.10959v3 Announce Type: replace-cross Abstract: While in-context learning (ICL) has achieved remarkable success in natural language and vision domains, its theoretical understanding-particul
Many AI agents in finance rely on extremely high quality context engineering from documents 📑 They can be roughly divided into two categories: 1️⃣ Repetitive, operational work common in back-office us
arXiv:2605.13050v1 Announce Type: cross Abstract: Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or nich
arXiv:2510.27055v2 Announce Type: replace Abstract: We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large
arXiv:2605.11414v1 Announce Type: new Abstract: While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial pre
arXiv:2603.17510v2 Announce Type: replace Abstract: Robots operating in human-shared environments must not only achieve task-level navigation objectives such as safety and efficiency, but also adapt t
arXiv:2605.11051v1 Announce Type: cross Abstract: LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promis
arXiv:2605.12412v1 Announce Type: new Abstract: Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent
arXiv:2605.09463v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces h
arXiv:2602.02350v2 Announce Type: replace Abstract: Multi-Agent Discussion (MAD) has garnered increasing attention very recently, where multiple LLM instances collaboratively solve problems via struct
arXiv:2509.15519v2 Announce Type: replace Abstract: This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local action
arXiv:2605.10268v1 Announce Type: cross Abstract: To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerge