Search: “guardrails”

arXiv:2606.09735v2 Announce Type: replace Abstract: The ambition behind alignment training is to make large language models safe and useful. The primary mechanisms, reinforcement learning from human f

arXiv:2609.18135v1 Announce Type: cross Abstract: State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. How

arXiv:2609.18605v1 Announce Type: cross Abstract: As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and fin

arXiv:2609.19072v1 Announce Type: new Abstract: Large language models are increasingly used for content moderation, but most evaluations still report aggregate accuracy on individual benchmarks. We in

arXiv:2609.18128v1 Announce Type: new Abstract: Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orche

arXiv:2609.18272v1 Announce Type: new Abstract: Agentic AI systems plan, invoke tools and act with limited supervision; they are now both the subject of audits and, increasingly, the auditor. Independ

arXiv:2609.16183v1 Announce Type: cross Abstract: Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture c

arXiv:2609.17247v1 Announce Type: new Abstract: An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a

arXiv:2508.02312v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine t

arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluci

arXiv:2609.12839v2 Announce Type: replace-cross Abstract: The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posin

arXiv:2609.10707v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines threat intelligence but introduces critical vulner

arXiv:2609.11176v1 Announce Type: new Abstract: Industrial query-to-agent matching fails when topical relevance is mistaken for executable capability, especially on long-tail and boundary-sensitive re

arXiv:2607.09770v2 Announce Type: replace Abstract: Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may

arXiv:2609.11758v1 Announce Type: new Abstract: Allowing large language models (LLMs) to retrieve information from a set of trusted documents can increase reliability and reduce hallucination. However

arXiv:2609.06543v1 Announce Type: new Abstract: Enterprise AI is evolving into an Enterprise Operating System where autonomous AI agents can plan, reason, use memory, invoke tools, execute workflows,

arXiv:2609.10397v1 Announce Type: cross Abstract: Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is

arXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod

arXiv:2609.05540v1 Announce Type: new Abstract: Many medical conditions require diagnosis through detailed, multi-context clinical assessment rather than from visual appearance alone. Despite this, vi

arXiv:2609.05850v1 Announce Type: new Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reveale

arXiv:2609.04871v1 Announce Type: new Abstract: Improving an industrial recommender is an iterative research-and-engineering process rather than a direct path from idea to deployment. In extbf{DASHEN,

arXiv:2609.02730v1 Announce Type: new Abstract: Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user beh

arXiv:2609.02316v1 Announce Type: cross Abstract: Generative engine optimization (GEO) enables content producers to increase the visibility of their web pages in generative search engines, but the sam

arXiv:2609.02560v1 Announce Type: new Abstract: Four-dimensional (4D) Radar is a powerful sensing modality capable of detecting surrounding three-dimensional (3D) objects under diverse weather conditi

arXiv:2606.17506v2 Announce Type: replace Abstract: Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judge

arXiv:2608.30065v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains tra

arXiv:2608.30050v1 Announce Type: new Abstract: Building a blockchain digital twin largely requires translating domain knowledge and specific system descriptions into a simulator architecture, calibra

arXiv:2603.22341v2 Announce Type: replace-cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capt

arXiv:2608.26154v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into digital health platforms to generate summaries of complex medical data. Although t

arXiv:2608.26124v1 Announce Type: new Abstract: Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evol

arXiv:2606.19660v2 Announce Type: replace-cross Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applicatio

arXiv:2608.23663v1 Announce Type: cross Abstract: Aligning deployed language models requires knowing when their outputs can be trusted, yet on-device models now ship to hundreds of millions of devices

arXiv:2608.24040v1 Announce Type: new Abstract: Enterprise AI agents in production often need to be bounded, stateful, observable, and governable rather than fully autonomous. We present PinSieve, a p

arXiv:2608.24650v1 Announce Type: cross Abstract: System-level simulation is an essential tool for exploring the rapidly expanding design space of LLM serving systems, where real deployments remain co

arXiv:2501.10573v2 Announce Type: replace Abstract: We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension. Viewing transfo

arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently beni

arXiv:2608.12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or

arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signa

arXiv:2608.11224v1 Announce Type: new Abstract: Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or

arXiv:2608.11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes th

arXiv:2608.10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions

arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these

arXiv:2607.14945v2 Announce Type: replace Abstract: State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Pr

arXiv:2510.04399v3 Announce Type: replace Abstract: We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes. Within this framework

arXiv:2608.10224v1 Announce Type: new Abstract: Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making

arXiv:2608.10153v1 Announce Type: new Abstract: Enterprises are deploying autonomous AI agents faster than they can govern them, and prevailing approaches stretch a single discipline, typically DevSec