Knowledge catalogue
arXiv:2609.21749v1 Announce Type: new Abstract: Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further
arXiv:2609.22056v1 Announce Type: cross Abstract: Multi-hop retrieval failures are not uniformly distributed across queries: they cluster in structurally predictable subpopulations. We prove two resul
Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi
Amazon SageMaker AI shipped 13 inference launches in the first half of 2026 across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch,
Vacations give you time to think and explore. I came across a few things and made a few discoveries of my own. It turns out that, as a programmer, I no longer need the smartest and most expensive AI m
arXiv:2609.20752v1 Announce Type: cross Abstract: Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Lo
arXiv:2609.19391v1 Announce Type: new Abstract: LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and secur
arXiv:2609.19183v1 Announce Type: cross Abstract: Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or
arXiv:2609.20732v1 Announce Type: new Abstract: Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched contex
arXiv:2609.19903v1 Announce Type: new Abstract: Accurate simulation is crucial for autonomous driving development, yet capturing real-world traffic complexity remains challenging. Existing simulators
arXiv:2609.20186v1 Announce Type: new Abstract: Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff betwee
arXiv:2609.19702v1 Announce Type: new Abstract: Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastr
arXiv:2609.18338v1 Announce Type: cross Abstract: Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted
arXiv:2609.18041v1 Announce Type: cross Abstract: Multi-encoder fusion extends Large Audio-Language Models (LALMs) beyond speech-centric recognition, but selecting encoders via intuition or exhaustive
arXiv:2609.18126v1 Announce Type: new Abstract: Agentic AI systems often approach the same task through multiple workflows that differ in reasoning strategy, verification structure, and compute cost.
arXiv:2609.18385v1 Announce Type: new Abstract: Emotions are an essential aspect of human communication, particularly on social media, where authors frequently combine text and images to convey their
arXiv:2609.18384v1 Announce Type: cross Abstract: We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains
arXiv:2609.17547v1 Announce Type: new Abstract: AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement
arXiv:2609.18481v1 Announce Type: new Abstract: Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases
arXiv:2609.17842v1 Announce Type: cross Abstract: Conversational visual analytics (CVA) agents powered by large language models generate visualizations and natural-language explanations from open-ende
arXiv:2609.18445v1 Announce Type: new Abstract: Agent skills, reusable procedural documents that extend LLM agents beyond their parametric memory, have become an important interface for deploying agen
arXiv:2609.17653v1 Announce Type: cross Abstract: GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate p
arXiv:2609.17775v1 Announce Type: new Abstract: Enterprise guideline documents mix narrative text, complex tables, and embedded images, and converting them into structured work artifacts still takes t
Schmidhuber was building recursive self-improving systems back in 1987. His new post covers four decades of RSI, from meta-evolution and self-modifying policies to the Gödel Machine and modern LLM age
Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide 'six reports on unexpected or concerning model behavior we’ve observed in the
arXiv:2609.18949v1 Announce Type: cross Abstract: We introduce StableEval Arena, a cost-aware benchmark framework for evaluating agentic AI systems on stablecoin peg-risk prediction. StableEval Arena
arXiv:2609.17686v1 Announce Type: cross Abstract: Three recent results describe what look like unrelated LLM reliability problems. Yin et al. (2026) show reasoning RL collapses tool-reliability repres
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with
arXiv:2609.16309v1 Announce Type: new Abstract: Despite the rapid progress of LLM-based agents for planning, code generation, and debugging, their practical value for tabular machine learning remains
arXiv:2609.16496v1 Announce Type: cross Abstract: AI policies introduced by software organisations to mitigate LLM-related risks such as sensitive information leaks and unauthorised usage are not usef
model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625) model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle ov
arXiv:2609.16096v1 Announce Type: cross Abstract: Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interpr
arXiv:2609.17241v1 Announce Type: new Abstract: While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates a
arXiv:2609.17416v1 Announce Type: new Abstract: Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply. We show that continuous-time cogn
arXiv:2609.16461v1 Announce Type: cross Abstract: Agentic large language model (LLM) systems rely on long interaction histories to preserve instructions, tool states, intermediate decisions, and unres
arXiv:2609.16887v1 Announce Type: new Abstract: Long-horizon reasoning is vulnerable to early errors that compromise later decisions. We present QART, the Quantum-Augmented Reasoning Transformer, a qu
arXiv:2609.07595v2 Announce Type: replace-cross Abstract: The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appears
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o
arXiv:2512.18021v4 Announce Type: replace-cross Abstract: In trapped-ion quantum computers, qubits must be shuttled between segments to interact. The routing logic that schedules these movements is wr
arXiv:2609.17260v1 Announce Type: new Abstract: Cyber-Physical Systems (CPS) operate through a continuous sense-compute-act loop within an open context environment, making it impossible to anticipate
arXiv:2609.16391v1 Announce Type: cross Abstract: Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embe
arXiv:2609.16215v1 Announce Type: new Abstract: GPU high bandwidth memory is scarce and expensive, and KV caches consume much of it as chats, agent loops, and document question answering accumulate st
arXiv:2404.03028v4 Announce Type: replace Abstract: Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in
arXiv:2609.14738v1 Announce Type: new Abstract: Automated reviewing systems are increasingly evaluated based on the quality of the reviews they produce. Yet a review is only useful if acting on it lea
arXiv:2609.13543v1 Announce Type: new Abstract: LLM agents are predominantly benchmarked on short, single-task trajectories, yet real deployments run for hours under contention, surfacing a different
arXiv:2609.15624v1 Announce Type: cross Abstract: Researchers assessing competent generative-AI use at work must choose among self-reports, objective tests, and measures of oversight and reliance. We
arXiv:2511.13725v5 Announce Type: replace-cross Abstract: Malicious AI causing harm to humans is not just a Hollywood fantasy. Indeed, as highly capable models such as Claude Mythos emerge and agent s
arXiv:2609.13860v1 Announce Type: new Abstract: Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data wit
arXiv:2609.13800v1 Announce Type: new Abstract: Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effect
arXiv:2511.03728v2 Announce Type: replace Abstract: On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memor
arXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach
arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infere
arXiv:2609.14374v1 Announce Type: cross Abstract: Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remain
arXiv:2609.14687v1 Announce Type: new Abstract: Data-to-text driver coaching is often presented as a generic pipeline from telematics events to advice. This paper argues that its content requires loca
arXiv:2609.15017v1 Announce Type: cross Abstract: Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under d
arXiv:2609.15194v1 Announce Type: new Abstract: When a direct proof of a statement S seems hard or even impossible to obtain, there may exist another statement (or set of statements) S^{*}, somehow re
arXiv:2609.15544v1 Announce Type: cross Abstract: Enabling human stakeholders to specify reward functions that lead to their desired outcomes is a key challenge in deploying reinforcement learning age
arXiv:2609.13995v1 Announce Type: new Abstract: Debate over synthetic data in marketing research has polarized between claims that large language models (LLMs) make human respondents obsolete and call
arXiv:2609.13334v1 Announce Type: cross Abstract: Enterprise AI agents often succeed in a demonstration and then stall once they must operate day after day. An industry report estimates that most pilo
arXiv:2609.15079v1 Announce Type: cross Abstract: Multi-agent LLM architectures, such as LangChain and AutoGen, largely assume English as the lingua franca for internal inter-agent communication, even