Cover Image

Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Junjun, Liu, Yixin, Miao, Rui, Ding, Kaize, Zheng, Yu, Nguyen, Quoc Viet Hung, Liew, Alan Wee-Chung, Pan, Shirui
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models
by: Li, Shiyuan, et al.
Published: (2026)

Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
by: Pan, Junjun, et al.
Published: (2025)

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
by: Shen, Xu, et al.
Published: (2025)

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
by: Li, Shiyuan, et al.
Published: (2025)

CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection
by: Pan, Junjun, et al.
Published: (2026)

Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations
by: Qiu, Zhangchi, et al.
Published: (2024)

A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection
by: Pan, Junjun, et al.
Published: (2025)

Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
by: Liu, Yujing, et al.
Published: (2026)

Decision-Level Fusion for Robust Wearable Affect Recognition
by: Singh, Lokesh, et al.
Published: (2026)

GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
by: Chen, Hongjiang, et al.
Published: (2026)

Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning
by: Cao, Hoang-Loc, et al.
Published: (2026)

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems
by: Wang, Shilong, et al.
Published: (2025)

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark
by: Wang, Yili, et al.
Published: (2024)

HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems
by: Xia, Yihan, et al.
Published: (2025)

Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
by: Hu, Zhengding, et al.
Published: (2026)

Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
by: Qiu, Zhangchi, et al.
Published: (2025)

Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation
by: Fang, Weiwei, et al.
Published: (2026)

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning
by: Huang, Rui Jerry, et al.
Published: (2025)

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling
by: Zhou, Jialong, et al.
Published: (2025)

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
by: Park, Hyunjee, et al.
Published: (2026)

Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems
by: Qiu, Zhangchi, et al.
Published: (2023)

INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
by: Zhou, Yijin, et al.
Published: (2026)

Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning
by: Bui, The Viet, et al.
Published: (2025)

ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization
by: Bui, The Viet, et al.
Published: (2024)

O-MAPL: Offline Multi-agent Preference Learning
by: Bui, The Viet, et al.
Published: (2025)

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
by: Wang, Ziqing, et al.
Published: (2025)

FINER-SQL: Boosting Small Language Models for Text-to-SQL
by: Hoang, Thanh Dat, et al.
Published: (2026)

A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback
by: Hoang, Thanh Dat, et al.
Published: (2025)

United We Stand: Decentralized Multi-Agent Planning With Attrition
by: Nguyen, Nhat, et al.
Published: (2024)

Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
by: Yang, Ruiyi, et al.
Published: (2025)

ConvoyLLM: Dynamic Multi-Lane Convoy Control Using LLMs
by: Lu, Liping, et al.
Published: (2025)

SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration
by: Zhao, Di, et al.
Published: (2026)

SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents
by: Hamblin, Grant, et al.
Published: (2026)

YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning
by: Zhuang, Yuan, et al.
Published: (2024)

MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations
by: Bui, The Viet, et al.
Published: (2025)

Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning (Extended Version)
by: Nguyen, Nhat D. A., et al.
Published: (2026)

LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce
by: Nguyen, Hao N., et al.
Published: (2026)

MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning
by: Venugopal, Aravind, et al.
Published: (2023)

ASAP: an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training
by: Ding, Yuran, et al.
Published: (2025)

Variational Auto-encoder Based Solutions to Interactive Dynamic Influence Diagrams
by: Pan, Yinghui, et al.
Published: (2024)