Imagen de Portada

Information Retrieval Induced Safety Degradation in AI Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Cheng, Stroebl, Benedikt, Yang, Diyi, Papakyriakopoulos, Orestis
Formato:	Preprint
Publicado:	2025
Materias:	Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Should AI Safety Benchmarks Benchmark Safety?
por: Yu, Cheng, et al.
Publicado: (2026)

Position: Measure Dataset Diversity, Don't Just Claim It
por: Zhao, Dora, et al.
Publicado: (2024)

Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators
por: Hutiri, Wiebke, et al.
Publicado: (2024)

Engaged AI Governance: Addressing the Last Mile Challenge Through Internal Expert Collaboration
por: Jarvers, Simon, et al.
Publicado: (2026)

AI Adoption Across Mission-Driven Organizations
por: Ali, Dalia, et al.
Publicado: (2025)

Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce
por: Shao, Yijia, et al.
Publicado: (2025)

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents
por: Li, Miles Q., et al.
Publicado: (2026)

No AI After Auschwitz? Bridging AI and Memory Ethics in the Context of Information Retrieval of Genocide-Related Information
por: Makhortykh, Mykola
Publicado: (2024)

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
por: Staufer, Leon, et al.
Publicado: (2026)

SWE-chat: Coding Agent Interactions From Real Users in the Wild
por: Baumann, Joachim, et al.
Publicado: (2026)

Auditing Agent Harness Safety
por: Liu, Chengzhi, et al.
Publicado: (2026)

SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery
por: Anugraha, David, et al.
Publicado: (2026)

Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables
por: Simmering, Paul F., et al.
Publicado: (2025)

Unintended Impacts of LLM Alignment on Global Representation
por: Ryan, Michael J., et al.
Publicado: (2024)

Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
por: Ali, Dalia, et al.
Publicado: (2025)

AI Safety for Everyone
por: Gyevnar, Balint, et al.
Publicado: (2025)

Mapping the Spiral of Silence: Surveying Unspoken Opinions in Online Communities
por: Zhao, Dora, et al.
Publicado: (2025)

The Role of AI Safety Institutes in Contributing to International Standards for Frontier AI Safety
por: Fort, Kristina
Publicado: (2024)

Sycophantic AI makes human interaction feel more effortful and less satisfying over time
por: Ibrahim, Lujain, et al.
Publicado: (2026)

AI Safety in Generative AI Large Language Models: A Survey
por: Chua, Jaymari, et al.
Publicado: (2024)

Safety First: Psychological Safety as the Key to AI Transformation
por: Reich, Aaron, et al.
Publicado: (2026)

Questionnaire Responses Do not Capture the Safety of AI Agents
por: Hellrigel-Holderbaum, Max, et al.
Publicado: (2026)

AI Safety, Alignment, and Ethics (AI SAE)
por: Waldner, Dylan
Publicado: (2025)

Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future
por: Li, Minzhi, et al.
Publicado: (2024)

The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulations
por: Mangold, Benedikt
Publicado: (2025)

Safety cases for frontier AI
por: Buhl, Marie Davidsen, et al.
Publicado: (2024)

The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
por: Si, Chenglei, et al.
Publicado: (2025)

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
por: Si, Chenglei, et al.
Publicado: (2024)

Offloading Score: Measuring AI Reliance Through Counterfactual Workflows
por: Padmakumar, Vishakh, et al.
Publicado: (2026)

Opportunities and Risks of Generative AI through the Health Information Journey
por: DeVerna, Matthew R., et al.
Publicado: (2026)

The BIG Argument for AI Safety Cases
por: Habli, Ibrahim, et al.
Publicado: (2025)

Persuasion and Safety in the Era of Generative AI
por: Kong, Haein
Publicado: (2025)

International AI Safety Report 2026
por: Bengio, Yoshua, et al.
Publicado: (2026)

AI Agents That Matter
por: Kapoor, Sayash, et al.
Publicado: (2024)

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
por: Li, Jing-Jing, et al.
Publicado: (2024)

AI Safety is Stuck in Technical Terms -- A System Safety Response to the International AI Safety Report
por: Dobbe, Roel
Publicado: (2025)

Evaluating AI Providers' Frontier Safety Frameworks
por: Stelling, Lily, et al.
Publicado: (2025)

A Grading Rubric for AI Safety Frameworks
por: Alaga, Jide, et al.
Publicado: (2024)

Astra: AI Safety, Trust, & Risk Assessment
por: Aggarwal, Pranav, et al.
Publicado: (2026)

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
por: Qiu, Jiahao, et al.
Publicado: (2025)