Search: “safety”

Christine Mui / Politico: California Gov. Gavin Newsom signs into law two bills, backed by Anthropic and OpenAI, regulating how outside groups evaluate AI for safety — SAN FRANCISCO — California Gov.

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

arXiv:2511.12018v2 Announce Type: replace Abstract: Traffic safety analysis at signalized intersections is essential for reducing vehicle and pedestrian collisions, yet traditional crash-based studies

OpenAI is on the cusp of releasing its most powerful AI model yet, Astra, following weeks of delays to shore up safety protocols after its agents attacked real targets during testing. As details about

arXiv:2608.30585v1 Announce Type: new Abstract: Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model woul

arXiv:2608.26533v1 Announce Type: cross Abstract: Autonomous driving motion planners generate and select candidate trajectories while accounting for interactions with surrounding agents. However, thes

arXiv:2608.26755v1 Announce Type: new Abstract: Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, re

arXiv:2603.13558v2 Announce Type: replace-cross Abstract: We introduce Holographic Invariant Storage (HIS), a protocol that assembles known properties of bipolar Vector Symbolic Architectures into a d

arXiv:2608.23972v1 Announce Type: new Abstract: Safety-aware motion planning remains a challenge in robotics, especially when missions are time-critical and are under complex specifications. In this p

arXiv:2608.23563v1 Announce Type: cross Abstract: Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete cras

arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with

arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From advers

arXiv:2608.18089v1 Announce Type: cross Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests t

Ina Fried / Axios: OpenAI changed safety practices and paused RL training for two weeks after the Hugging Face breach and evidence Astra may have met a critical cyber threshold — OpenAI said Tuesday t

arXiv:2608.14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather tha

arXiv:2608.14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing me

arXiv:2607.16943v2 Announce Type: replace Abstract: Safety validation at signalized intersections remains a critical bottleneck for the deployment of autonomous driving systems (ADS), as these scenari

arXiv:2608.10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do

arXiv:2608.08485v1 Announce Type: new Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inf

arXiv:2608.06378v1 Announce Type: cross Abstract: Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions. Existing studies mainly focus on drive

arXiv:2608.05594v1 Announce Type: cross Abstract: Validation adequacy in safety-critical software depends on more than the system under test. Critical scenarios must be constructed under controlled co

arXiv:2608.02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish compl

arXiv:2607.29203v1 Announce Type: new Abstract: Deploying drone swarms to track a dynamic target in cluttered environments presents severe computational and safety challenges. We propose MROPE, a hier

arXiv:2607.27626v1 Announce Type: new Abstract: Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Inform

arXiv:2603.14841v3 Announce Type: replace-cross Abstract: Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer l

arXiv:2607.15166v2 Announce Type: replace Abstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? W

arXiv:2512.05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their 'open' nature introduces more avenues fo

Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss. We’re sharing what we learned from studying a long-running

arXiv:2607.13078v1 Announce Type: cross Abstract: LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature

arXiv:2607.12406v1 Announce Type: new Abstract: The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequentl

arXiv:2607.03135v1 Announce Type: cross Abstract: Maintaining consistency between architectural design and runtime-observed behavior is challenging in long-lived safety-critical firmware. This paper p

arXiv:2606.20408v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under

arXiv:2606.28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods

arXiv:2606.29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations

arXiv:2603.15282v2 Announce Type: replace Abstract: Learned action policies are increasingly popular in sequential decision-making, but suffer from a lack of safety guarantees. Recent work introduced

arXiv:2606.25629v1 Announce Type: new Abstract: Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the un

arXiv:2606.23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes the

arXiv:2510.06492v2 Announce Type: replace Abstract: Latent world models are a promising approach for learning state representations and dynamics directly from high-dimensional observations, enabling r

arXiv:2606.09165v1 Announce Type: new Abstract: Safety judges are increasingly deployed to evaluate model outputs against evolving criteria, yet recent meta-evaluation work shows they remain brittle u

arXiv:2606.08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy. Althoug

arXiv:2606.08531v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, a

arXiv:2606.05952v1 Announce Type: new Abstract: In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model s

arXiv:2606.06423v1 Announce Type: new Abstract: Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions. Existing diffu

arXiv:2606.03954v1 Announce Type: new Abstract: As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible conse

arXiv:2606.00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dy

arXiv:2512.20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rel