Knowledge catalogue
arXiv:2606.02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and e
arXiv:2508.21448v3 Announce Type: replace Abstract: Large language models (LLMs) sometimes refuse to follow benign instructions, such as declining to argue a political position or adopt a stated perso
This is disaster from Meta AI. Imagine being able to hack high profile accounts like White House, the U.S. Space Force, and Sephora simply by chatting with a support bot. why would an AI chatbot be al
arXiv:2509.20941v2 Announce Type: replace Abstract: As surgical AI transitions from pixel-level detection to complex reasoning, Scene Graphs (SGs) offer the structured, relational representations nece
arXiv:2605.31138v1 Announce Type: cross Abstract: User Experience Research (UXR) in a legal and regulatory contexts presents unique challenges that require specialised approaches to protect vulnerable
AI agents possess incredible reasoning capabilities and can perform increasingly complex actions. But the reliability of agentic outcomes depends entirely on the quality of the context they can access
arXiv:2605.29801v1 Announce Type: new Abstract: Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhi
Welcome to the second Cloud CISO Perspectives for May 2026. Today, Usman Chaudhary, Field CISO, Google Public Sector, offers a guide for CISOs protecting government agencies and critical infrastructur
arXiv:2604.01604v2 Announce Type: replace Abstract: While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior fo
arXiv:2605.27851v1 Announce Type: new Abstract: Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational
arXiv:2605.26954v1 Announce Type: new Abstract: Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically underserved.
arXiv:2605.27117v1 Announce Type: new Abstract: AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing ha
arXiv:2510.19420v2 Announce Type: replace-cross Abstract: Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent desig
arXiv:2605.26275v1 Announce Type: new Abstract: Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed
arXiv:2510.17759v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplor
arXiv:2605.24216v1 Announce Type: cross Abstract: Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horiz
arXiv:2605.25454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LL
arXiv:2605.22634v2 Announce Type: replace-cross Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings
arXiv:2602.04653v4 Announce Type: replace-cross Abstract: Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor at
Amazon Bedrock AgentCore payments is now available in preview, it provides instant payments to paid external services with no manual billing setup per provider, stablecoin support for cost-effective m
arXiv:2605.24069v1 Announce Type: cross Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented
Pope Leo has warned that the artificial intelligence revolution is being driven primarily by profit motives rather than ethical considerations, characterizing this as a form of 'idolatry of profit.' T
arXiv:2605.20704v1 Announce Type: cross Abstract: Autonomous AI agents that spawn sub-agent swarms create a safety gap: existing credential revocation mechanisms, OAuth~2.0 introspection, OCSP, and W3
arXiv:2602.06500v2 Announce Type: replace Abstract: Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promi
arXiv:2410.15362v2 Announce Type: replace-cross Abstract: Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks t
arXiv:2605.19219v1 Announce Type: new Abstract: A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistica
arXiv:2605.18988v1 Announce Type: cross Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary atta
arXiv:2605.16309v1 Announce Type: new Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operato
arXiv:2605.17228v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the
arXiv:2512.23978v2 Announce Type: replace Abstract: Generative artificial intelligence (GenAI) is shifting from conversational assistants toward agentic systems -- autonomous decision-making systems t
arXiv:2605.17734v1 Announce Type: new Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizo
arXiv:2605.16268v1 Announce Type: cross Abstract: Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the a
arXiv:2605.18672v1 Announce Type: new Abstract: This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for
arXiv:2605.17036v1 Announce Type: new Abstract: This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We identify four inference-time levers that s
arXiv:2605.18338v1 Announce Type: cross Abstract: Champion recommendation in multiplayer online battle arena games is usually framed informally as a problem of metagame strength, personal comfort, or
arXiv:2410.02832v2 Announce Type: replace-cross Abstract: This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we
arXiv:2512.06655v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity obj
arXiv:2601.06366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently s
arXiv:2605.14750v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks
arXiv:2605.14418v1 Announce Type: cross Abstract: 'Oh-Oh, yes, I'm the great pretender. Pretending that I'm doing well. My need is such, I pretend too much...' summarizes the state in the area of jail
arXiv:2605.12840v1 Announce Type: cross Abstract: Marketplace platforms routinely evaluate pricing and allocation policies using logged observational data, yet strong offline performance does not impl
arXiv:2605.12869v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that ci
arXiv:2605.11307v1 Announce Type: new Abstract: Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Exis
arXiv:2605.09222v1 Announce Type: cross Abstract: Logs are ubiquitous in modern systems. Unfortunately, their unstructured nature in flat sequences limits understanding of execution behaviors, hinderi
Intelligent trust is not just a bonus for artificial intelligence systems, but a vital factor in their success. Although the AI train doesn’t seem to be slowing down any time soon, security concerns a
arXiv:2601.21410v3 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as st
arXiv:2510.08592v3 Announce Type: replace-cross Abstract: Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best out
arXiv:2501.03544v5 Announce Type: replace-cross Abstract: Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, the
arXiv:2605.08518v1 Announce Type: new Abstract: Competition retrospectives are useful when they explain what a leaderboard measured, how hidden evaluation changed conclusions, and which design pattern
arXiv:2510.20129v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses des
arXiv:2509.02372v3 Announce Type: replace-cross Abstract: Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training int
arXiv:2601.00889v2 Announce Type: replace Abstract: FANOS{} is a PyTorch optimizer that augments RMS-preconditioned momentum with a scalar feedback controller over update energy. The public reference
arXiv:2605.07982v1 Announce Type: new Abstract: Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimension
arXiv:2605.07399v1 Announce Type: new Abstract: Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable
arXiv:2503.06223v5 Announce Type: replace Abstract: Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is
arXiv:2605.01143v1 Announce Type: new Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, the
arXiv:2603.00822v2 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents increasingly execute complex, autonomous software engineering tasks, developers rely on natural language
arXiv:2605.03228v1 Announce Type: cross Abstract: As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that
arXiv:2605.03788v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time
arXiv:2605.03351v1 Announce Type: new Abstract: Video vision-language models (VLMs) keep paying for visual state the stream already told us was stable. The factory wall did not move, but most VLM pipe