Cover Image

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Zihan, Zhu, Dongsheng, Liu, Shudong, Zhang, Taolin, Liu, Junnan, Li, Qingqiu, Luo, Minnan, Zhang, Songyang, Chen, Kai
Format:	Preprint
Published:	2025
Subjects:	Multiagent Systems Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Verification for LLM Code Generation: From Generation to Testing
by: Ma, Zihan, et al.
Published: (2025)

Rethinking Priority Scheduling for Sequential Multi-Agent Decision Making in Stackelberg Games
by: Liu, Xiangyu, et al.
Published: (2026)

AutoGenesisAgent: Self-Generating Multi-Agent Systems for Complex Tasks
by: Harper, Jeremy
Published: (2024)

Coding Triangle: How Does Large Language Model Understand Code?
by: Zhang, Taolin, et al.
Published: (2025)

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
by: Chen, Kai, et al.
Published: (2025)

Origin-Destination Pattern Effects on Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning
by: Fan, Muyang, et al.
Published: (2025)

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
by: Liu, Junnan, et al.
Published: (2025)

Skill Description Deception Attack against Task Routing in Internet of Agents
by: He, Jiayi, et al.
Published: (2026)

A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
by: Liu, Zijun, et al.
Published: (2023)

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
by: Gou, Wanshuang, et al.
Published: (2026)

Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
by: Shi, Lu, et al.
Published: (2024)

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
by: Zhang, Lingxi, et al.
Published: (2026)

The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
by: Liu, Jiayuan, et al.
Published: (2026)

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
by: Zhang, Shaokun, et al.
Published: (2025)

A Group Consensus-Driven Auction Algorithm for Cooperative Task Allocation Among Heterogeneous Multi-Agents
by: Wang, Gang, et al.
Published: (2025)

From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
by: Yao, Chang, et al.
Published: (2025)

MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
by: Chen, Jiayi, et al.
Published: (2026)

Multi-Agent Synchronization Tasks
by: Fernandez, Rolando, et al.
Published: (2024)

A BDI Agent-Based Task Scheduling Framework for Cloud Computing
by: Yang, Yikun, et al.
Published: (2024)

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
by: Liu, Zhiwei, et al.
Published: (2024)

Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs
by: Mao, Yuren, et al.
Published: (2025)

DISPATCH -- Decentralized Informed Spatial Planning and Assignment of Tasks for Cooperative Heterogeneous Agents
by: Liu, Yao, et al.
Published: (2025)

Distributed Task Allocation for Multi-Agent Systems: A Submodular Optimization Approach
by: Liu, Jing, et al.
Published: (2024)

VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft
by: Dong, Yubo, et al.
Published: (2024)

From Task Allocation to Risk Clearing: A Unifying Interface for Mixed Human-Agent Societies
by: Vassiliades, Vassilis
Published: (2026)

Position: Emergent Machina Sapiens Urge Rethinking Multi-Agent Paradigms
by: Li, Hepeng, et al.
Published: (2025)

CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness
by: Song, Shoucheng, et al.
Published: (2025)

MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
by: Zhang, Ming, et al.
Published: (2025)

Strategic Concealment of Environment Representations in Competitive Games
by: Guan, Yue, et al.
Published: (2025)

Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
by: Bisconti, Piercosma, et al.
Published: (2025)

COLA: A Scalable Multi-Agent Framework For Windows UI Task Automation
by: Zhao, Di, et al.
Published: (2025)

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
by: Jin, Chang, et al.
Published: (2026)

Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution
by: Luo, Zixun, et al.
Published: (2026)

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
by: Shen, Siqi, et al.
Published: (2023)

KAOS: Large Model Multi-Agent Operating System
by: Zhuo, Zhao, et al.
Published: (2024)

Emergence in Multi-Agent Systems: A Safety Perspective
by: Altmann, Philipp, et al.
Published: (2024)

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
by: Fourney, Adam, et al.
Published: (2024)

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
by: Li, Simin, et al.
Published: (2025)

Agent System Operations: Categorization, Challenges, and Future Directions
by: Wang, Zexin, et al.
Published: (2026)

Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery
by: Zhang, Yue, et al.
Published: (2025)