Knowledge catalogue
arXiv:2609.38460v1 Announce Type: new Abstract: Language agents must revise planned actions when evidence changes, permission is revoked, or a stop instruction arrives. A useful response is selective:
arXiv:2609.39229v1 Announce Type: cross Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary fro
arXiv:2609.38491v1 Announce Type: new Abstract: Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Ye
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couple
arXiv:2609.38530v1 Announce Type: new Abstract: Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window
arXiv:2609.38712v1 Announce Type: new Abstract: Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value ca
arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly const
arXiv:2609.39662v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for AI-generated image (AIGI) detection, providing natural-language explanations for authenticity ju
arXiv:2607.18446v2 Announce Type: replace Abstract: Purpose: Understanding how much of routine policing involves vulnerable people could inform resourcing, training, and multi-agency response, yet adm
arXiv:2609.39846v1 Announce Type: cross Abstract: We investigate the problem of role-capability leakage (RCL), in which a role-prompted reasoning model generates convincing in-role text while continui
arXiv:2609.38161v1 Announce Type: new Abstract: Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We
arXiv:2609.36920v1 Announce Type: new Abstract: Comprehensive evaluations of automatic speech recognition (ASR) for Iberian languages remain limited, and low-resource languages, biases, and efficiency
arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leav
arXiv:2609.37807v1 Announce Type: new Abstract: Studying how fine-tuning shapes refusal and noncompliance behaviour requires identifying training examples that refuse, evade or otherwise fail to fulfi
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s
arXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task
arXiv:2609.36221v1 Announce Type: new Abstract: The way a model distributes activity over each layer's attention heads offers a coarse view of how it routes information through depth; how this changes
arXiv:2609.37891v1 Announce Type: new Abstract: Current pre-training datasets are derived from web crawls, with all their issues, and were not designed to support mid- and post-training pipelines--for
arXiv:2609.36695v1 Announce Type: new Abstract: Self-distillation turns knowledge distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external teac
arXiv:2609.36139v1 Announce Type: cross Abstract: As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outpu
arXiv:2609.33886v2 Announce Type: replace Abstract: Large language models are trained to always produce an answer, regardless of whether they possess the relevant knowledge, which leads them to fabric
arXiv:2609.36214v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematica
arXiv:2609.36070v1 Announce Type: cross Abstract: AI accelerator systems are rapidly consolidating into scale-up architectures, where tens to thousands of GPUs communicate over high-bandwidth, single-
arXiv:2609.36322v1 Announce Type: cross Abstract: Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of
arXiv:2609.35928v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly
arXiv:2609.36605v1 Announce Type: new Abstract: Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We intro
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template
arXiv:2609.37046v1 Announce Type: new Abstract: Vision-Language Models are increasingly used in autonomous-driving systems, yet their ability to recover dynamic physical state from visual input remain
arXiv:2609.36290v1 Announce Type: cross Abstract: We investigate the extent to which the Hamas attacks on Israel of October 7, 2023, have affected German social media debates about Judaism and Israel.
Top tech executives met with President Donald Trump on Tuesday to discuss the future of artificial intelligence amid growing concerns over AI models losing control. Researchers and lawmakers are calli
arXiv:2609.37680v1 Announce Type: cross Abstract: One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can t
arXiv:2609.35832v1 Announce Type: cross Abstract: Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes,
arXiv:2609.37494v1 Announce Type: new Abstract: Multiple-choice benchmarks are cheap to grade and are running out of room, and the standard remedy, writing harder items, is slow and repeated for every
arXiv:2609.33467v1 Announce Type: new Abstract: When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order,
arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation
arXiv:2506.08140v2 Announce Type: replace Abstract: Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-qualit
arXiv:2609.32961v1 Announce Type: new Abstract: As LLM agents tackle longer tasks, they increasingly compress growing histories of reasoning, actions, and tool outputs. Compression can reduce token us
arXiv:2609.33052v1 Announce Type: cross Abstract: Financial question answering often requires precise numerical extraction, unit handling, and arithmetic over tables and text, but applying expensive v
arXiv:2609.33261v1 Announce Type: new Abstract: Multimodal engineering benchmarks largely evaluate static understanding, such as recognizing components, interpreting diagrams, or answering technical q
arXiv:2609.33965v1 Announce Type: cross Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between input (pre
arXiv:2609.34798v1 Announce Type: cross Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effectiv
arXiv:2609.34572v1 Announce Type: cross Abstract: Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for th
Hi, I'm a long time subscriber of their pro plan. In the past, they were adding the open weight models to their catalog as soon as they dropped. Since this new change in their payment plans, I haven't
arXiv:2609.31651v1 Announce Type: new Abstract: Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) hand
arXiv:2609.33646v1 Announce Type: cross Abstract: Browser-use agents require seamless alignment between structured web metadata and visual information, while preserving relevant context across long in
arXiv:2609.33638v1 Announce Type: new Abstract: We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for pro
arXiv:2609.32802v1 Announce Type: cross Abstract: One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebu
arXiv:2609.33065v1 Announce Type: cross Abstract: Large language model (LLM) assistants can now search the web and consult external sources while completing user requests. These sources can provide us
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun
arXiv:2609.34970v1 Announce Type: new Abstract: Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated
Kanishka Singh / Reuters: Trump releases a voluntary AI accord with tech leaders, asking companies to partner with external auditors and set up internal controls to monitor AI alignment — President Do
arXiv:2609.34771v1 Announce Type: cross Abstract: Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model int
arXiv:2609.30483v1 Announce Type: cross Abstract: Audio language models state numbers for acoustic quantities, and neither human opinion nor a judge model says whether such a number is true of the sig
Artificial Analysis: Artificial Analysis launches the Cyber Index Alliance with partners Collinear, IBM, Nvidia, and Vercel to evaluate how AI agents find and fix vulnerabilities — The Artificial Anal
arXiv:2609.31054v1 Announce Type: new Abstract: Large Language Model (LLM) pollution occurs when synthetic responses contaminate data intended to capture human behavior. High deployment costs have so
Some context first. I am process improvement / business consultant and had worked with Fortune 500 companies on improving their processes around refunds, returns, customer support, etc. This entire th
arXiv:2609.31563v1 Announce Type: new Abstract: Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contrib
arXiv:2609.31511v1 Announce Type: new Abstract: We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (N