Search: “safety”

arXiv:2610.15934v1 Announce Type: new Abstract: Motion planning for automated vehicles in interactive traffic has to simultaneously ensure safety, respect traffic rules, and maintain comfortable progr

arXiv:2610.14482v1 Announce Type: new Abstract: Autonomous Aerial Vehicle (AAV) trajectory planning requires real-time and accurate safety gradient guidance, especially in dynamic environments. Existi

arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local

arXiv:2603.02225v3 Announce Type: replace Abstract: Learning from feedback advances the capabilities and safety of frontier models, but preference supervision remains costly and difficult to scale. We

arXiv:2604.06058v2 Announce Type: replace-cross Abstract: Safety-critical control of uncertain, adaptive systems often relies on conservative, worst-case uncertainty bounds that limit closed-loop perf

arXiv:2610.10321v1 Announce Type: cross Abstract: Road safety programs count the coded fields of police crash records, while the officer's narrative, which often records factors the fields omit, is ra

arXiv:2610.07083v1 Announce Type: cross Abstract: Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness

arXiv:2610.08578v1 Announce Type: new Abstract: Transformers provide a state-of-the-art modeling framework, yet poor calibration limits their reliability in safety-critical applications. A promising d

arXiv:2610.05563v1 Announce Type: cross Abstract: Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for

arXiv:2610.05346v1 Announce Type: new Abstract: Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversa

arXiv:2603.11413v4 Announce Type: replace-cross Abstract: A recent Nature Medicine study reported that ChatGPT Health under-triages 51.6% of emergencies and concluded that consumer-facing AI triage po

arXiv:2610.02224v1 Announce Type: new Abstract: Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical R

arXiv:2610.00208v1 Announce Type: cross Abstract: This paper studies decentralized safe path following for multiple quadrotors on intersecting paths, where safety requires both collision avoidance and

arXiv:2609.39145v1 Announce Type: cross Abstract: Unreliable visual inputs can harm task performance and cause potential physical safety risks for vision-language-action (VLA) models. We analyze how p

arXiv:2609.39486v1 Announce Type: new Abstract: Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operatio

arXiv:2609.38205v1 Announce Type: new Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the trans

For months, people have wondered when OpenAI will go public. CEO Sam Altman says it won't happen until the company can make better promises about model safety, with no firm timeline in sight. 'We inte

In July, AI agents running a security test escaped their sandbox and ended up inside @huggingface's servers. So today we're happy to be among @nvidia and @JensenHuang's partners on the release of the

arXiv:2609.31553v1 Announce Type: new Abstract: Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the ca

Tomek Korbak is a full time OpenAI employee working on misalignment. In his message here, he says AI continues to break out of their best secure environments. In reply to a comment, he says we all are

arXiv:2609.29381v1 Announce Type: new Abstract: Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effecti

arXiv:2609.27763v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on explicit chain-of-thought (CoT) reasoning and large context windows to achieve strong performance on complex tasks

arXiv:2609.25905v1 Announce Type: new Abstract: This paper presents a modular control barrier function (CBF) framework for safe free-flying robotic spacecraft operations during tumbling target capture

arXiv:2609.22178v1 Announce Type: cross Abstract: Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task

arXiv:2609.22048v1 Announce Type: new Abstract: A selective predictor acts as a safety gate: it returns an output only when the prediction appears sufficiently trustworthy. Deployments increasingly re

These are precisely the scenarios that I spend a significant time actually being concerned with. The adoption of unreliable, brittle, and inaccurate LLMs within safety-critical fields (e.g., defense a

arXiv:2609.19124v1 Announce Type: new Abstract: Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formati

arXiv:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the in

arXiv:2609.16189v1 Announce Type: new Abstract: Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries, institutions, escalation, plan brittleness, doctrine,

arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing

The world deserves confidence that American companies developing increasingly capable AI will act responsibly, especially as the trajectory of progress has steepened. Every frontier lab must deliver o

arXiv:2606.13720v2 Announce Type: replace Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recove

arXiv:2509.21545v3 Announce Type: replace Abstract: The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but th

arXiv:2609.09650v1 Announce Type: new Abstract: Reinforcement learning (RL) has demonstrated considerable potential for autonomous driving decision-making. However, its deployment in urban autonomous

arXiv:2609.08186v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed t

arXiv:2609.05591v1 Announce Type: cross Abstract: Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which

arXiv:2609.06061v1 Announce Type: new Abstract: Termination-based constrained reinforcement learning is attractive for safety-critical robotic deployments: it avoids online optimization at inference,

A senior Anthropic safety researcher has said there is more than a 10 percent chance artificial intelligence 'could kill all humans' by the end of the decade, just hours after a colleague resigned ove

Interestingly, by being visibly incompetent and malicious in a way that encourages regulators to take notice, OpenAI may be doing more for AI safety than almost anyone else. How we think about the “wi

arXiv:2508.00935v3 Announce Type: replace-cross Abstract: Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if m

arXiv:2609.03454v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly benefi

arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mech

arXiv:2609.00076v1 Announce Type: new Abstract: Clinical artificial intelligence is increasingly embedded in real-world care, yet existing safety mechanisms are poorly suited to reconstructing and lea

arXiv:2609.00904v1 Announce Type: new Abstract: Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study

arXiv:2608.29109v1 Announce Type: new Abstract: Large language models often answer structurally unanswerable questions, such as computing cot(-540{eg}) or evaluating (1).startswith('1'), instead of ab

arXiv:2608.29458v1 Announce Type: cross Abstract: Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluation