Search: “safety”

arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break

arXiv:2605.28097v1 Announce Type: new Abstract: Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo R

arXiv:2605.27948v1 Announce Type: new Abstract: Motorcycles face disproportionately high crash risks compared to cars due to limited protection and heightened sensitivity to surface hazards, yet Advan

arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary

arXiv:2605.27046v1 Announce Type: new Abstract: Motor thermal management is often overlooked in the context of electrically-actuated robots, particularly legged robots, but motor overheating is a key

arXiv:2605.24270v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of mode

arXiv:2605.23989v1 Announce Type: new Abstract: Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks

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:2605.22643v1 Announce Type: new Abstract: Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follo

arXiv:2605.20203v1 Announce Type: cross Abstract: As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities

arXiv:2605.21496v1 Announce Type: cross Abstract: Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmar

Since its earliest days back in office, the Trump administration has been going after researchers who study and try to counter hate speech, harassment, propaganda, and disinformation online. Now, some

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Tech researchers are suing the Trump administration over the f

arXiv:2603.11768v2 Announce Type: replace Abstract: Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong m

arXiv:2605.19722v1 Announce Type: cross Abstract: Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Sin

arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active ac

arXiv:2605.17268v1 Announce Type: new Abstract: We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 10

arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag

arXiv:2605.10146v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces criti

This post highlights a contradiction in AI industry arguments, contrasting Western tech company claims that regulation will disadvantage them competitively against China with evidence of China's own s

Google LLC, Microsoft Corp. and xAI have agreed to share unreleased versions of their artificial intelligence models with the U.S. Department of Commerce to ensure the technologies do not pose a threa

arXiv:2605.04039v1 Announce Type: new Abstract: Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation

arXiv:2605.02526v1 Announce Type: cross Abstract: Barrier certificates are scalar functions over the state space of dynamical systems that separate all unsafe states from all reachable states. The exi

arXiv:2605.02777v1 Announce Type: new Abstract: Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a s

arXiv:2605.01051v1 Announce Type: cross Abstract: While Bellman equations for basic reach, avoid, and reach-avoid problems are well studied, the relationship between value optimality and policy optima

arXiv:2605.01133v1 Announce Type: cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on compl

arXiv:2604.14858v2 Announce Type: replace Abstract: As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve

arXiv:2604.05310v2 Announce Type: replace Abstract: Navigating autonomous underwater vehicles (AUVs) in unknown environments is significantly challenging due to poor visibility, weak signal transmissi

arXiv:2604.24618v1 Announce Type: new Abstract: We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier

arXiv:2604.24074v1 Announce Type: new Abstract: Safety benchmarks such as HarmBench rely on LLM judges to classify model responses as harmful or safe, yet the judge configuration, namely the combinati

arXiv:2603.21697v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visual

arXiv:2604.18487v1 Announce Type: new Abstract: The Adversarial Humanities Benchmark (AHB) evaluates whether model safety refusals survive a shift away from familiar harmful prompt forms. Starting fro

arXiv:2602.07954v4 Announce Type: replace Abstract: As Large Language Models (LLMs) become increasingly deployed in Polish language applications, the need for efficient and accurate content safety cla

arXiv:2604.16541v1 Announce Type: new Abstract: Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an

arXiv:2601.06116v2 Announce Type: replace-cross Abstract: Generative AI models reproduce the biases in the training data and can further amplify them through mode collapse. We refer to the resulting h

arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory do

arXiv:2604.07879v1 Announce Type: new Abstract: Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content

arXiv:2610.21789v1 Announce Type: cross Abstract: Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime catego

arXiv:2610.19267v1 Announce Type: cross Abstract: Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong d

At AI Engineer New York, OpenAI and Anthropic presented how to give financial agents useful autonomy while keeping consequential decisions under control. The consensus was that safe autonomy depends o

arXiv:2610.15486v1 Announce Type: new Abstract: Robotic systems for lunar surface operations must act autonomously and preserve their own integrity in an environment where failures are unrecoverable a

arXiv:2610.11934v1 Announce Type: cross Abstract: Industrial environments are increasingly characterized by the tight interaction among physical processes, communication infrastructures, and intellige

arXiv:2606.13994v2 Announce Type: replace-cross Abstract: LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world.

arXiv:2610.02874v1 Announce Type: new Abstract: Scalable driving simulators typically execute vehicle commands using prescribed behavioral or kinematic rules, overlooking the physics of tire-road inte

arXiv:2609.40007v1 Announce Type: cross Abstract: A vision-language-action (VLA) policy can finish a manipulation task while knocking over objects unrelated to it, so task success alone does not show

arXiv:2609.37126v1 Announce Type: new Abstract: Safe navigation against obstacles that can actively maneuver within bounded capabilities remains challenging: robust control barrier function methods ty