Image de couverture de livre

RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Xiuyuan, Zhao, Jian, Yuan, Yuchen, Zhang, Tianle, Zhou, Huilin, Zhu, Zheng, Hu, Ping, Kong, Linghe, Zhang, Chi, Huang, Weiran, Li, Xuelong
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
par: Zhang, Zhen, et autres
Publié: (2026)

A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
par: Cho, Ha Na
Publié: (2026)

Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows
par: Yu, Tao, et autres
Publié: (2026)

HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics
par: Jiang, Shufan, et autres
Publié: (2025)

Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
par: Liu, Shuo, et autres
Publié: (2026)

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
par: Zhang, Yang, et autres
Publié: (2024)

MARS-DA: A Hierarchical Reinforcement Learning Framework for Risk-Aware Multi-Agent Bidding in Power Grids
par: Chen, Jiayi, et autres
Publié: (2026)

Subgoal-based Hierarchical Reinforcement Learning for Multi-Agent Collaboration
par: Xu, Cheng, et autres
Publié: (2024)

Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
par: Bisconti, Piercosma, et autres
Publié: (2025)

MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
par: Zhang, Ming, et autres
Publié: (2025)

RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
par: Liu, Jun, et autres
Publié: (2025)

Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
par: Shi, Lu, et autres
Publié: (2024)

The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models
par: Lu, Dakuan, et autres
Publié: (2025)

Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
par: Jian, HuaDong, et autres
Publié: (2026)

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
par: Chen, Kai, et autres
Publié: (2025)

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
par: Ma, Zihan, et autres
Publié: (2025)

GAWM: Global-Aware World Model for Multi-Agent Reinforcement Learning
par: Shi, Zifeng, et autres
Publié: (2025)

Spatiotemporal Attention-Augmented Inverse Reinforcement Learning for Multi-Agent Task Allocation
par: Yin, Huilin, et autres
Publié: (2025)

LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration
par: Qu, Zheyan, et autres
Publié: (2025)

Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception
par: Zha, Jirong, et autres
Publié: (2026)

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
par: Chen, Handi, et autres
Publié: (2026)

Multi-Agent Digital Twinning for Collaborative Logistics: Framework and Implementation
par: Xu, Liming, et autres
Publié: (2023)

Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning
par: Wang, Qian, et autres
Publié: (2024)

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
par: Binkyte, Ruta
Publié: (2025)

Training Generalizable Collaborative Agents via Strategic Risk Aversion
par: Qu, Chengrui, et autres
Publié: (2026)

Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
par: Yang, Jing, et autres
Publié: (2026)

Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
par: Cuadros, Diego F., et autres
Publié: (2026)

Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
par: Kostka, Adam, et autres
Publié: (2025)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
par: Zhang, Boxuan, et autres
Publié: (2025)

YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning
par: Zhuang, Yuan, et autres
Publié: (2024)

Evaluating Collective Behaviour of Hundreds of LLM Agents
par: Willis, Richard, et autres
Publié: (2026)

SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration
par: Zhao, Di, et autres
Publié: (2026)

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
par: Wang, Chenyu, et autres
Publié: (2026)

SniffySquad: Patchiness-Aware Gas Source Localization with Multi-Robot Collaboration
par: Cheng, Yuhan, et autres
Publié: (2024)

A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
par: Liu, Zijun, et autres
Publié: (2023)

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
par: He, Zeyu, et autres
Publié: (2026)

The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
par: Reza, Zarreen
Publié: (2025)

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
par: Liu, Zhiwei, et autres
Publié: (2024)

AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
par: Li, Yang, et autres
Publié: (2025)

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
par: Zhang, Yuxin, et autres
Publié: (2026)