Search: “safety”

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

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

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:2610.15486v1 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

arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model tha

arXiv:2609.27900v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate

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:2609.19630v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creat

arXiv:2609.17292v1 Announce Type: new Abstract: Control barrier functions for input-constrained systems place the admissible input set inside the definition of the safe set, yet the resulting barrier

arXiv:2512.01037v3 Announce Type: replace-cross Abstract: As safety alignment becomes standard in large language models, refusal behavior has become an important part of model reliability. However, mo

arXiv:2609.13866v1 Announce Type: new Abstract: Group-relative policy optimization (GRPO and descendants) can discard no-contrast rollout groups through dynamic sampling, while practical implementatio

arXiv:2609.09793v1 Announce Type: cross Abstract: Directional ablation removes an aligned language model's ability to refuse by projecting a single 'refusal direction' out of the weights that write th

arXiv:2608.30201v1 Announce Type: new Abstract: Directly robustifying small-signal stability in AC optimal power flow is challenging since the stability boundary in the original uncertainty space is i

arXiv:2608.21570v1 Announce Type: new Abstract: Deploying a safety layer for large language models on commodity hardware is constrained by the guards available to do it: current open guard models hold