Cover Image

Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Pengzhou, Dong, Lingzhong, Wu, Zeng, Wu, Zongru, Tang, Xiangru, Qin, Chengwei, Zhang, Zhuosheng, Liu, Gongshen
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
by: Wu, Zheng, et al.
Published: (2025)

Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
by: Dong, Lingzhong, et al.
Published: (2025)

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
by: Wu, Zongru, et al.
Published: (2025)

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
by: Wu, Zongru, et al.
Published: (2025)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
by: Wu, Zongru, et al.
Published: (2024)

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
by: Cheng, Pengzhou, et al.
Published: (2025)

OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents
by: Wu, Zheng, et al.
Published: (2026)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
by: Wu, Zongru, et al.
Published: (2024)

Faithful Mobile GUI Agents with Guided Advantage Estimator
by: Hu, Haowen, et al.
Published: (2026)

OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents
by: Cheng, Pengzhou, et al.
Published: (2025)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
by: Cheng, Pengzhou, et al.
Published: (2024)

MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
by: Cheng, Pengzhou, et al.
Published: (2024)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
by: Cheng, Pengzhou, et al.
Published: (2024)

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements
by: Ju, Tianjie, et al.
Published: (2025)

VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
by: Wu, Zheng, et al.
Published: (2025)

On the Adaptive Psychological Persuasion of Large Language Models
by: Ju, Tianjie, et al.
Published: (2025)

Transferring Backdoors between Large Language Models by Knowledge Distillation
by: Cheng, Pengzhou, et al.
Published: (2024)

Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System
by: Guo, Yuan, et al.
Published: (2025)

Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities
by: Ju, Tianjie, et al.
Published: (2024)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
by: Zhao, Haodong, et al.
Published: (2025)

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
by: Yuan, Tongxin, et al.
Published: (2024)

MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
by: Tang, Xiangru, et al.
Published: (2023)

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning
by: Xia, Peng, et al.
Published: (2025)

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review
by: Cheng, Pengzhou, et al.
Published: (2023)

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
by: Zhao, Haodong, et al.
Published: (2025)

You Only Look at Screens: Multimodal Chain-of-Action Agents
by: Zhang, Zhuosheng, et al.
Published: (2023)

DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
by: Yan, Kaiwen, et al.
Published: (2025)

Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
by: Zou, Anni, et al.
Published: (2023)

MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
by: Tang, Xiangru, et al.
Published: (2025)

ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
by: Tang, Xiangru, et al.
Published: (2025)

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
by: Ouyang, Siru, et al.
Published: (2025)

Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
by: Wu, Zheng, et al.
Published: (2026)

CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
by: Ma, Xinbei, et al.
Published: (2024)

LocAgent: Graph-Guided LLM Agents for Code Localization
by: Chen, Zhaoling, et al.
Published: (2025)

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
by: Ma, Xinbei, et al.
Published: (2024)

Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
by: Wu, Yexin, et al.
Published: (2024)

Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
by: Sun, Haoran, et al.
Published: (2025)

GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents
by: Diao, Lingxiao, et al.
Published: (2025)

PresentAgent-2: Towards Generalist Multimodal Presentation Agents
by: Wu, Wei, et al.
Published: (2026)

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
by: Lu, Yichen, et al.
Published: (2025)