Knowledge catalogue
Erik Wasson / Bloomberg: House Speaker Johnson says there's “potentially” a role for Congress in creating AI guardrail legislation and that he plans to hold a meeting with AI executives — House Speake
arXiv:2609.12216v1 Announce Type: new Abstract: Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavio
arXiv:2603.10068v2 Announce Type: replace-cross Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to c
Even though I made this graph, it is also kind of wrong. Fable is guardrailed Mythos. If we use the Mythos date I took the new AA-Briefcase scores from @ArtificialAnlys (basically having the AI do mul
arXiv:2606.22873v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the
arXiv:2606.01513v1 Announce Type: cross Abstract: High-stakes enterprise document generation, including financial dispute narratives, compliance notices, and audit summaries, demands schema correctnes
arXiv:2606.01472v1 Announce Type: cross Abstract: High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierar
arXiv:2602.15853v2 Announce Type: replace-cross Abstract: We propose a lightweight explainable guardrail (LEG) method to detect unsafe prompts. LEG uses a multi-task learning architecture to jointly l
arXiv:2601.18491v2 Announce Type: replace Abstract: The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current gua
arXiv:2606.15396v2 Announce Type: replace-cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety g
arXiv:2610.02074v1 Announce Type: new Abstract: Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomo
arXiv:2609.29573v1 Announce Type: new Abstract: Text-to-SQL systems are increasingly deployed on production databases, where queries that pass benchmark evaluation can still produce results that disto
arXiv:2608.17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Exis
arXiv:2605.29251v1 Announce Type: new Abstract: As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates
arXiv:2605.29659v1 Announce Type: cross Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak
arXiv:2609.32801v1 Announce Type: cross Abstract: Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during exec
As threat actors increasingly use AI to accelerate and develop cyberattacks, enterprise defenders need to rely on both AI and a critical defender’s advantage: Business context that only you possess. E
arXiv:2609.39086v1 Announce Type: cross Abstract: Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and b
arXiv:2608.11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.Recent work shows that dropping a stan
Learn how evaluation-driven development, agent harnesses, AI observability, guardrails, and cost-per-outcome metrics move AI agents from pilot to production. The post Evaluation-driven development: Ho
arXiv:2605.13076v2 Announce Type: replace Abstract: The LLM-based generation of machine-readable outputs such as JSON has attracted significant attention for integration with external systems. However
arXiv:2605.05704v2 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and
arXiv:2605.08463v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed in open social environments, yet the relationship between their configuration specifications and their em
As AI coding agents become deeply embedded in developer workflows, defenders must evolve their definition of malicious files and rethink how to protect against them. Autonomous AI agents operate acros
I was unable to retrieve the specific content from the X (Twitter) post at the URL provided, and my web search did not surface the original post or any reliable secondary sources quoting or summari...
As artificial intelligence matures, the security guardrails — and the computer system itself — are changing. This week, the conversation centered around agents going rogue. Better guardrails are neede
Florida has sought a temporary injunction against OpenAI, arguing that large‑language model development without third‑party approved safety guardrails poses an existential threat and preys on vulnerab
arXiv:2608.26306v1 Announce Type: new Abstract: A large language model (LLM) guardrail for a self-adaptive system (SAS) may issue an approval that is correct at check time but stale by actuation. This
arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a
arXiv:2609.09090v1 Announce Type: cross Abstract: Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations t
arXiv:2608.14680v1 Announce Type: new Abstract: Reliability in LLM-based agentic systems is a property of the whole execution (its tool calls, model calls, guardrails, and inter-agent messages), not o
arXiv:2608.10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formula
arXiv:2610.07276v1 Announce Type: cross Abstract: Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification
arXiv:2606.15034v2 Announce Type: replace Abstract: Computer-use agents can complete benign user instructions while violating important constraints of the user's environment. We introduce OSGuard, a d
arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialec
arXiv:2608.30703v1 Announce Type: cross Abstract: Runtime guardrails are essential for reliable large language model (LLM) deployment, yet existing approaches typically rely on independent, external m
arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke
arXiv:2605.14454v1 Announce Type: cross Abstract: As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line
arXiv:2609.24996v1 Announce Type: new Abstract: Behavior cloning for robot manipulation relies on expert demonstrations. However, for tasks that require dynamic stability, precise contact timing, or d
arXiv:2609.16204v1 Announce Type: cross Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and project
With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a
The AI era demands a fundamental shift in security, and that includes identity and access management (IAM). Traditional controls simply aren’t built for autonomous AI agents that interact with sensiti
arXiv:2609.27773v1 Announce Type: cross Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents in
In this episode of The Agent Factory, we explore the reality of building with autonomous agents alongside Ryan Lopopolo, a software engineer at Google Cloud and the person who coined the term agent ha
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:2609.00487v1 Announce Type: cross Abstract: Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-
arXiv:2608.19579v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating c
arXiv:2606.30932v1 Announce Type: new Abstract: Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's expe
AI browsers can be manipulated through prompt injection or memory poisoning to create false operational contexts where they bypass security guardrails, treating harmful actions as game logic rather th
arXiv:2606.08247v1 Announce Type: cross Abstract: Acute asthma risk assessment requires rapid interpretation of respiratory sounds, oxygenation, airflow limitation, speech ability, work of breathing,
arXiv:2606.03136v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails: they operate on individual turns, while attacks
arXiv:2605.28647v1 Announce Type: new Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped
arXiv:2605.13044v1 Announce Type: cross Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, b
arXiv:2610.06744v1 Announce Type: cross Abstract: ufakzeka-karar is an open Turkish decision model with 182,494,466 parameters. Given a Turkish text and questions of a fixed answer type (a choice, a l
Quite the combination of arrogance and incompetence over there at OpenAI: Yup, part of the transformation of enterprise architects into orchestrators is the technical ability to put guardrails on AI a
Wood Mackenzie built APEX, a shared agentic AI platform on Amazon Bedrock AgentCore so every team can ship production agents without rebuilding runtime, identity, observability, and guardrails from sc
not the man we need at this moment Q: The worst case is that AI will turn against humanity. Do we have guardrails? Trump: It's going to be fine. We'll always have something to stop them. We'll have a
arXiv:2609.08634v1 Announce Type: new Abstract: Integrating robust safety guardrails into Large Language Models (LLMs) is essential for delivering helpful yet harmless responses. While proprietary sys