Imagen de Portada

SafePro: Evaluating the Safety of Professional-Level AI Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Kaiwen, Jangam, Shreedhar, Nagarajan, Ashwin, Polu, Tejas, Oruganti, Suhas, Liu, Chengzhi, Kuo, Ching-Chen, Zheng, Yuting, Narayanaraju, Sravana, Wang, Xin Eric
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
por: Zhou, Kaiwen, et al.
Publicado: (2025)

GRIT: Teaching MLLMs to Think with Images
por: Fan, Yue, et al.
Publicado: (2025)

Multimodal Situational Safety
por: Zhou, Kaiwen, et al.
Publicado: (2024)

AgentWall: A Runtime Safety Layer for Local AI Agents
por: Aravind, Ashwin
Publicado: (2026)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
por: Zhou, Kaiwen, et al.
Publicado: (2025)

Duality and Interpolation of Bergman Spaces
por: Bhat, Shreedhar
Publicado: (2024)

Behavioral Signatures in Action: Advancing Real-Time Fraud Prevention through Intelligent Analytics
por: Sharath Reddy Polu
Publicado: (2025)

DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance
por: Govil, Shreedhar, et al.
Publicado: (2025)

Self-Resource Allocation in Multi-Agent LLM Systems
por: Amayuelas, Alfonso, et al.
Publicado: (2025)

Smells Like Fire: Exploring the Impact of Olfactory Cues in VR Wildfire Evacuation Training
por: Crosby, Alison, et al.
Publicado: (2026)

The Name-Free Gap: Policy-Aware Stylistic Control in Music Generation
por: Nagarajan, Ashwin, et al.
Publicado: (2025)

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

Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
por: Oruganti, Venkatakrishna Reddy
Publicado: (2026)

Perception-to-Pursuit: Track-Centric Temporal Reasoning for Open-World Drone Detection and Autonomous Chasing
por: Oruganti, Venkatakrishna Reddy
Publicado: (2026)

Multi-user QKD using quotient graph states derived from continuous-variable dual-rail cluster states
por: Oruganti, Akash nag
Publicado: (2024)

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations
por: Liu, Chengzhi, et al.
Publicado: (2025)

An Activity-Theoretical Approach to Teacher Professional Development in Pedagogical AI Agent Design
por: Xin, Haiyang, et al.
Publicado: (2026)

Stability of the Monomial Basis Kernel of Reinhardt domains
por: Bhat, Shreedhar, et al.
Publicado: (2026)

Predictive Bayesian Arbitration: A Scalable Noisy-OR Model with Service Criticality Awareness
por: Jangam, Anil, et al.
Publicado: (2026)

On the dimension of the $p$-Bergman spaces
por: Bhat, Shreedhar, et al.
Publicado: (2025)

ClawSafety: "Safe" LLMs, Unsafe Agents
por: Wei, Bowen, et al.
Publicado: (2026)

A Safe Harbor for AI Evaluation and Red Teaming
por: Longpre, Shayne, et al.
Publicado: (2024)

AI Safety Training Can be Clinically Harmful
por: BN, Suhas, et al.
Publicado: (2026)

Influence of Dapagliflozin Dosing on Low‐Density Lipoprotein Cholesterol in Type 2 Diabetes Mellitus: A Systematic Literature Review and Meta‐Analysis
por: Srinivas Martha, et al.
Publicado: (2024)

Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA
por: Fan, Yue, et al.
Publicado: (2024)

Why Cognitive Robotics Matters: Lessons from OntoAgent and LLM Deployment in HARMONIC for Safety-Critical Robot Teaming
por: Oruganti, Sanjay, et al.
Publicado: (2026)

Flow to Learn: Flow Matching on Neural Network Parameters
por: Saragih, Daniel, et al.
Publicado: (2025)

SafeArena: Evaluating the Safety of Autonomous Web Agents
por: Tur, Ada Defne, et al.
Publicado: (2025)

Three‐Phase Line‐Frequency Rectifier With Multiple Input Voltage Levels
por: Hideo Pratama, et al.
Publicado: (2025)

"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
por: Gu, Jing, et al.
Publicado: (2025)

Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making
por: Wang, Kaifeng, et al.
Publicado: (2025)

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
por: Tang, Zhengyang, et al.
Publicado: (2026)

Editorial: Are Antidepressant Medications Safe in Inflammatory Bowel Disease? Authors' Reply
por: Bharati Kochar, et al.
Publicado: (2025)

Safety Pretraining: Toward the Next Generation of Safe AI
por: Maini, Pratyush, et al.
Publicado: (2025)

Be Pro Be Proud as a Water Professional
por: Will England
Publicado: (2024)

ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments
por: Ai, Jiaxin, et al.
Publicado: (2025)

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
por: Wang, Zhaoxin, et al.
Publicado: (2026)

Sodium‐Ion Conducting Tamarind Seed Polysaccharide‐NaBF 4 Solid Biopolymer Electrolytes: Ionic Conductivity and Electrochemical Performance
por: Anji Reddy Polu, et al.
Publicado: (2025)

Probing AI Safety with Source Code
por: Narayan, Ujwal, et al.
Publicado: (2025)

Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories
por: Zhang, Zihan, et al.
Publicado: (2026)