Search: “guardrails”

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:2608.11146v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. How

arXiv:2608.10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream dec

arXiv:2608.09900v1 Announce Type: new Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably wa

arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents

arXiv:2608.04065v1 Announce Type: cross Abstract: Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator a

arXiv:2608.03028v1 Announce Type: new Abstract: Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations

arXiv:2608.00180v1 Announce Type: new Abstract: Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two

arXiv:2608.02046v1 Announce Type: new Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and pro

arXiv:2607.26313v1 Announce Type: cross Abstract: Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost. The most dangerous enterprise defects are

arXiv:2603.15684v2 Announce Type: replace-cross Abstract: Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although

arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inputs, such as system prompts, should override confl

arXiv:2607.24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynam

arXiv:2607.24371v1 Announce Type: cross Abstract: Healthcare interoperability requires AI systems to produce structured outputs conforming to standardized schemas including ICD-10 for diagnostic codin

arXiv:2607.23147v1 Announce Type: cross Abstract: Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of t

arXiv:2607.22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns

arXiv:2607.22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk. Existi

arXiv:2607.21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verba

arXiv:2607.13705v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluat

arXiv:2512.01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety

arXiv:2601.22136v2 Announce Type: replace-cross Abstract: Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We in

arXiv:2510.14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jail

arXiv:2606.28332v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains p

arXiv:2606.20668v1 Announce Type: cross Abstract: LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI appli

arXiv:2606.05743v1 Announce Type: cross Abstract: Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifi

arXiv:2606.05183v1 Announce Type: new Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode. We

arXiv:2606.01481v1 Announce Type: new Abstract: With the rapid advancements in text-to-image diffusion models, generative video models (T2V models) like Sora can now produce short synthetic videos fro

arXiv:2505.11063v3 Announce Type: replace Abstract: LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly sh

arXiv:2605.18423v1 Announce Type: new Abstract: As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their

arXiv:2605.05630v2 Announce Type: replace Abstract: Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objec

arXiv:2510.04214v3 Announce Type: replace Abstract: We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The ag

arXiv:2604.24102v1 Announce Type: new Abstract: Synthesizing a reactive system from specifications given in linear temporal logic (LTL) is a classical problem, finding its applications in safety-criti

arXiv:2604.22436v1 Announce Type: new Abstract: The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable a

arXiv:2511.22277v2 Announce Type: replace Abstract: Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when

arXiv:2604.21744v1 Announce Type: cross Abstract: The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic

arXiv:2604.21793v1 Announce Type: new Abstract: In this paper, we develop a novel logic-based approach to detecting high-level temporally extended events from timestamped data and background knowledge

arXiv:2604.21896v1 Announce Type: new Abstract: This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxo

arXiv:2604.19827v1 Announce Type: cross Abstract: Software engineering faces a fundamental challenge: multi-agent AI systems fail in ways that defy explanation by traditional theories. While individua

arXiv:2604.20779v1 Announce Type: new Abstract: AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in pr

arXiv:2604.19124v1 Announce Type: new Abstract: Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity

arXiv:2508.14913v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, mul

arXiv:2506.02264v3 Announce Type: replace Abstract: Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often str

arXiv:2604.17215v1 Announce Type: new Abstract: Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compr

arXiv:2604.18510v1 Announce Type: cross Abstract: Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabi

arXiv:2604.17053v1 Announce Type: new Abstract: Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Resea

arXiv:2604.15384v1 Announce Type: cross Abstract: We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 env