Search: “safety”

arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effec

arXiv:2407.20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language und

arXiv:2606.08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a s

arXiv:2605.25956v2 Announce Type: replace Abstract: Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual re

arXiv:2606.04262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the

arXiv:2602.01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the u

arXiv:2606.03203v1 Announce Type: new Abstract: Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unv

arXiv:2606.03486v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translatio

arXiv:2606.03312v1 Announce Type: cross Abstract: While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robo

arXiv:2512.22539v2 Announce Type: replace-cross Abstract: While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively und

arXiv:2603.04444v3 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- se

arXiv:2606.02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceed

arXiv:2606.01028v1 Announce Type: new Abstract: Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements an

arXiv:2606.00168v1 Announce Type: new Abstract: AI systems are increasingly deployed in conversational settings where users may be uncertain whether they are speaking with a human or an AI. Despite mo

arXiv:2606.00566v1 Announce Type: cross Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party con

arXiv:2606.02041v1 Announce Type: new Abstract: Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate.

arXiv:2606.01169v1 Announce Type: cross Abstract: Spacecraft collision avoidance for low-thrust satellites often requires determining not only how to maneuver, but also how late a maneuver can begin w

arXiv:2605.31196v1 Announce Type: cross Abstract: Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already co

arXiv:2602.14399v2 Announce Type: replace Abstract: Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced t

arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new thr

arXiv:2605.27898v1 Announce Type: new Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores

arXiv:2605.27375v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context

arXiv:2605.27382v1 Announce Type: cross Abstract: A key promise of pluralistic AI is behavioral adaptation: persona prompts like 'be creative' or 'be thorough' let systems respect diverse user values

arXiv:2605.27997v1 Announce Type: cross Abstract: Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-leve

arXiv:2605.26918v1 Announce Type: new Abstract: Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generi

arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas

arXiv:2605.25984v1 Announce Type: cross Abstract: Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We presen

arXiv:2603.22348v3 Announce Type: replace Abstract: Online learning algorithms often face a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing

arXiv:2605.23157v1 Announce Type: new Abstract: The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures

arXiv:2605.22001v1 Announce Type: cross Abstract: Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives.

arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b

arXiv:2605.20296v1 Announce Type: new Abstract: Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon,

arXiv:2605.18915v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-

arXiv:2605.18309v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alig

arXiv:2605.16707v1 Announce Type: cross Abstract: The rapid evolution of digital health technologies is redefining healthcare services worldwide. The integration of wireless communication and Internet

arXiv:2510.07239v2 Announce Type: replace Abstract: Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack

arXiv:2605.15377v1 Announce Type: new Abstract: As AI systems are increasingly deployed in autonomous agentic settings at scale, it is important to ensure the actions they take are safe and aligned wi

arXiv:2506.08584v4 Announce Type: replace Abstract: Medical question answering (QA) benchmarks often focus on multiple-choice or fact-based tasks, leaving open-ended answers to real patient questions

arXiv:2605.13542v1 Announce Type: new Abstract: Intensive care units (ICU) generate long, dense and evolving streams of clinical information, where physicians must repeatedly reassess patient states u

arXiv:2605.11533v1 Announce Type: new Abstract: Clinical check-up reports are multimodal documents that combine page layouts, tables, numerical biomarkers, abnormality flags, imaging findings, and dom

arXiv:2603.28561v2 Announce Type: replace Abstract: The growing deployment of small Unmanned Aerial Systems (sUASs) in low-altitude airspaces has increased the need for reliable tactical deconfliction

arXiv:2601.01762v2 Announce Type: replace-cross Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. W

arXiv:2605.10067v1 Announce Type: cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing ap

arXiv:2605.03476v1 Announce Type: new Abstract: Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when perfor

arXiv:2605.02398v1 Announce Type: cross Abstract: As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not kn

arXiv:2605.00005v1 Announce Type: new Abstract: The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computati