Knowledge catalogue
arXiv:2610.00663v1 Announce Type: new Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing
arXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca
I have been building a somewhat unusual local inference machine around two Huawei Atlas 300I Duo cards. They are relatively inexpensive, passive, dual-accelerator PCIe cards with 96 GB of device memor
arXiv:2605.30521v1 Announce Type: new Abstract: Large language models must frequently process untrusted inputs, such as judging an answer from another model or running tasks like spam and harm classif
Social and low-evidence quarantine moved to raw as rejected. 168 high-specificity articles remain in inbox; four sources were filed.
Written by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb
arXiv:2603.19397v2 Announce Type: replace Abstract: Non-pharmaceutical interventions (NPIs), such as diagnostic testing and quarantine, are crucial for controlling infectious disease outbreaks but are
Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri
arXiv:2609.27883v1 Announce Type: cross Abstract: Closed-loop discovery systems increasingly execute experiments and update decisions autonomously, turning record integrity into part of the experiment
arXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adve
arXiv:2609.14744v1 Announce Type: new Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget,
arXiv:2608.10300v1 Announce Type: new Abstract: Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human re
arXiv:2606.02867v1 Announce Type: cross Abstract: Human behaviour during epidemics affects infectious disease dynamics, but quantifying this remains deeply challenging. Here we introduce the Epi-LLM f
arXiv:2604.27775v1 Announce Type: cross Abstract: Shallow nanoindentation enables mechanical characterization of thin films, individual phases and other volume-constrained materials, but measured hard
arXiv:2610.09906v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated al
arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt
arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion,
NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime that gives AI agents clear, enforceable boundaries. It traces
Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an announcem
arXiv:2609.19226v1 Announce Type: cross Abstract: AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a fin
arXiv:2609.12230v1 Announce Type: new Abstract: Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) pr
arXiv:2609.06140v1 Announce Type: cross Abstract: Agents can turn shared infrastructure into a channel for coordinated intrusion. The Hugging Face incident and a separate public-wiki investigation sho
arXiv:2608.29835v1 Announce Type: new Abstract: Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central f
arXiv:2607.09156v2 Announce Type: replace Abstract: Additive activation steering is calibrated in single-turn chat and then deployed inside agent scaffolds. The quantity usually reported for that move
arXiv:2608.24017v1 Announce Type: cross Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent
arXiv:2608.22338v1 Announce Type: new Abstract: Interactive PDF form fields are often absent from documents that visually resemble forms, leaving users unable to enter data without printing or externa
Hey guys, Inco AI shipped DFlash 2 a few days ago with a drafter for Qwen 3.8 27B and a llama.cpp PR. I built the PR and ran it against plain decoding, MTP, the n-gram lookup drafters, and my July DFl
arXiv:2608.19124v1 Announce Type: cross Abstract: Astrolinguistics -- communication with minds that categorize reality differently from ours -- has been purely speculative since Freudenthal's Lincos (
arXiv:2608.11632v1 Announce Type: cross Abstract: Persistent AI agents accumulate versioned state across long horizons, but storage retention alone does not identify authoritative state. Without an ex
arXiv:2608.01085v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduce
arXiv:2607.28829v1 Announce Type: cross Abstract: Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back in
arXiv:2607.24117v1 Announce Type: new Abstract: Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existi
arXiv:2601.17303v2 Announce Type: replace Abstract: As Industrial Internet of Things (IIoT) environments scale to tens of thousands of connected devices, centralized security architectures introduce l
arXiv:2607.06871v1 Announce Type: new Abstract: Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields infe
Prompt: ANNALS — a living kingdom in a single file Working title behavior: the app titles itself per seed — 'The Annals of Vaelmere', 'The Annals of Osterholt' — because the central conceit is that yo
arXiv:2607.03510v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-aug
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
Social engineering defense startup Doppel Inc. today launched Doppel Email Security, an agentic artificial intelligence layer that traces phishing messages back to attacker infrastructure and orchestr
AI safety and research company (PBC) that builds Claude — reliable, interpretable, steerable systems — and publishes frontier model and safety research.