Image de couverture de livre

AgentRob: From Virtual Forum Agents to Hijacked Physical Robots

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Wenrui, Wang, Yaxuan, Zhang, Xun, Wang, Yanshu, Wei, Jiashen, Xiang, Yifan, Wang, Yuhang, Ye, Mingshen, Dai, Elsie, Liu, Zhiqi, Xu, Yingjie, Chen, Xinyang, Sun, Hengzhe, Shen, Jiyu, He, Jingjing, Yang, Tong
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
par: Liu, Wenrui, et autres
Publié: (2025)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
par: Wang, Hongtao, et autres
Publié: (2026)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
par: Zhang, Yuanhe, et autres
Publié: (2025)

How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
par: Wang, Yanshu, et autres
Publié: (2026)

Can a Robot Walk the Robotic Dog: Triple-Zero Collaborative Navigation for Heterogeneous Multi-Agent Systems
par: Wang, Yaxuan, et autres
Publié: (2026)

Fabrication of Graphene Oxide/Covalent Organic Polymer‐Based Magnetic Composite for Efficient Extraction of Terazosin, Prazosin, and Alfuzosin
par: Mingshen Chen, et autres
Publié: (2025)

Towards Action Hijacking of Large Language Model-based Agent
par: Zhang, Yuyang, et autres
Publié: (2024)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
par: Sun, Jingwei, et autres
Publié: (2026)

Collaborative Medical Triage under Uncertainty: A Multi-Agent Dynamic Matching Approach
par: Cheng, Hongyan, et autres
Publié: (2025)

Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
par: Zhang, Xi, et autres
Publié: (2026)

Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information
par: Wang, Yanshu, et autres
Publié: (2024)

DocOS: Towards Proactive Document-Guided Actions in GUI Agents
par: Liu, Jingjing, et autres
Publié: (2026)

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
par: Mao, Yanxu, et autres
Publié: (2026)

Complexity and Algorithm for the Matching vertex-cutset Problem
par: Li, Hengzhe, et autres
Publié: (2025)

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
par: Aichberger, Lukas, et autres
Publié: (2025)

SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration
par: Cen, Jipeng, et autres
Publié: (2024)

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
par: Liu, Zhichao, et autres
Publié: (2026)

Automating Agent Hijacking via Structural Template Injection
par: Deng, Xinhao, et autres
Publié: (2026)

Developing a Multi-Agent System to Generate Next Generation Science Assessments with Evidence-Centered Design
par: Yang, Yaxuan, et autres
Publié: (2026)

On Non-KAM Invariant Circles for Area-Preserving Twist Maps
par: Guo, Jiashen, et autres
Publié: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
par: Ying, Zonghao, et autres
Publié: (2026)

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
par: Sun, Zeyi, et autres
Publié: (2025)

QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering
par: Wang, Yanshu, et autres
Publié: (2024)

M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery
par: Liu, Hanyi, et autres
Publié: (2026)

Diff-FlowFSI: A GPU-Optimized Differentiable CFD Platform for High-Fidelity Turbulence and FSI Simulations
par: Fan, Xiantao, et autres
Publié: (2025)

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
par: Liu, Yunqi, et autres
Publié: (2026)

Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks
par: Yang, Zijiao, et autres
Publié: (2024)

Behavioral Transfer in AI Agents: Evidence and Privacy Implications
par: Luo, Shilei, et autres
Publié: (2026)

The Study on the Localization of Acid Phosphatase Activity During Spermiogenesis in Chinese Mitten-Handed Crab, Eriocheir sinensis.
par: Liu, Guirong, et autres
Publié: (2007)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
par: Cheng, Zihao, et autres
Publié: (2026)

Strategic Learning for Disturbance Rejection in Multi‐Agent Systems: Nash and Minmax in Graphical Games
par: Xinyang Wang, et autres
Publié: (2025)

The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
par: Qian, Yaoyao, et autres
Publié: (2025)

Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
par: Sun, Zhaoyan, et autres
Publié: (2025)

A Fourth-Order Cut-cell Multigrid Method for Solving Elliptic Equations on Arbitrary Domains
par: Liu, Jiyu, et autres
Publié: (2026)

Social Isolation Trajectories Spanning Childhood to Adulthood and Mortality Risk in CKM Syndrome: Evidence From CHARLS
par: Luyue Liang, et autres
Publié: (2026)

Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
par: Wang, Chenxu, et autres
Publié: (2024)

AgentStudio: A Toolkit for Building General Virtual Agents
par: Zheng, Longtao, et autres
Publié: (2024)

Inception Attacks: Immersive Hijacking in Virtual Reality Systems
par: Yang, Zhuolin, et autres
Publié: (2024)

ClawGuard: Out-of-Band Detection of LLM Agent Workflow Hijacking via EM Side Channel
par: Gan, Leo Linqian, et autres
Publié: (2026)

Routine: A Structural Planning Framework for LLM Agent System in Enterprise
par: Zeng, Guancheng, et autres
Publié: (2025)