Copertina

Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kholkar, Gauri, Ahuja, Ratinder
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement
di: Kholkar, Gauri, et al.
Pubblicazione: (2025)

Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation
di: Kumar, Shanu, et al.
Pubblicazione: (2024)

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
di: Jin, Xisen, et al.
Pubblicazione: (2026)

A Lightweight Explainable Guardrail for Prompt Safety
di: Islam, Md Asiful, et al.
Pubblicazione: (2026)

Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents
di: Zhang, Xing, et al.
Pubblicazione: (2026)

Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems
di: Lee, Alexander W., et al.
Pubblicazione: (2025)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
di: Liu, Dongrui, et al.
Pubblicazione: (2026)

In AI Sweet Harmony: Sociopragmatic Guardrail Bypasses and Evaluation-Awareness in OpenAI gpt-oss-20b
di: Durner, Nils
Pubblicazione: (2025)

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
di: Owiredu-Ashley, Harry
Pubblicazione: (2026)

Meta Prompting for AI Systems
di: Zhang, Yifan, et al.
Pubblicazione: (2023)

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
di: She, Yining, et al.
Pubblicazione: (2025)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
di: Das, Saswat, et al.
Pubblicazione: (2026)

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
di: Li, Hao, et al.
Pubblicazione: (2024)

BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
di: Mazza, Arnon, et al.
Pubblicazione: (2026)

Building Guardrails for Large Language Models
di: Dong, Yi, et al.
Pubblicazione: (2024)

RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
di: Zhong, Haitian, et al.
Pubblicazione: (2026)

Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting
di: Javaji, Shashidhar Reddy, et al.
Pubblicazione: (2025)

Memory in the Age of AI Agents
di: Hu, Yuyang, et al.
Pubblicazione: (2025)

AI Governance and Accountability: An Analysis of Anthropic's Claude
di: Priyanshu, Aman, et al.
Pubblicazione: (2024)

Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
di: Chen, Wenyuan, et al.
Pubblicazione: (2025)

Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks
di: Gosmar, Diego, et al.
Pubblicazione: (2025)

WebGuard: Building a Generalizable Guardrail for Web Agents
di: Zheng, Boyuan, et al.
Pubblicazione: (2025)

PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games
di: Buongiorno, Steph, et al.
Pubblicazione: (2024)

From Threat Intelligence to Firewall Rules: Semantic Relations in Hybrid AI Agent and Expert System Architectures
di: Bonfanti, Chiara, et al.
Pubblicazione: (2026)

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
di: Chen, Haolin, et al.
Pubblicazione: (2026)

ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
di: Wang, Zhebo, et al.
Pubblicazione: (2026)

Trust-Oriented Adaptive Guardrails for Large Language Models
di: Hu, Jinwei, et al.
Pubblicazione: (2024)

From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making
di: Jain, Raunak
Pubblicazione: (2026)

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
di: Wang, Jian, et al.
Pubblicazione: (2025)

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
di: Kapoor, Sayash, et al.
Pubblicazione: (2025)

OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents
di: Thind, Raghav, et al.
Pubblicazione: (2025)

Holistic Evaluation and Failure Diagnosis of AI Agents
di: Madvil, Netta, et al.
Pubblicazione: (2026)

Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games
di: Nonomura, Ryota, et al.
Pubblicazione: (2024)

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
di: Giarrusso, Francesco, et al.
Pubblicazione: (2025)

Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails
di: Cheng, Kellen Tan, et al.
Pubblicazione: (2025)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
di: Sreedhar, Makesh Narsimhan, et al.
Pubblicazione: (2025)

Agent-Testing Agent: A Meta-Agent for Automated Testing and Evaluation of Conversational AI Agents
di: Komoravolu, Sameer, et al.
Pubblicazione: (2025)

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
di: Chen, Yurun, et al.
Pubblicazione: (2026)

Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI
di: Rosenfeld, Katherine A., et al.
Pubblicazione: (2024)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
di: Wang, Libo
Pubblicazione: (2024)