mlsanityData to 14 Oct 2026

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

arXiv 2505.19234 ↗First posted 25 May 2025cs.AI cs.CL cs.MAcited by 36

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilities, achieving state-of-the-art accuracy with efficient resource utilization. The code is available at https://github.com/JialongZhou666/GUARDIAN

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 42 of its 56 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

42 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attacks20 Feb
  2. 2023Evil Geniuses: Delving into the Safety of LLM-based Agents20 Nov

Other references · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
28 more
  1. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  2. 2016Deep Variational Information Bottleneckcited by 930
  3. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  4. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  5. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  6. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  7. 2023Self-collaboration Code Generation via ChatGPTcited by 258
  8. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
  9. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  10. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  11. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  12. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  13. 2020Graph Information Bottleneckcited by 168
  14. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 154
  15. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 128
  16. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  17. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 99
  18. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 93
  19. 2024Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applicationscited by 59
  20. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 56
  21. 2024MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debatecited by 56
  22. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 45
  23. 2023Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedbackcited by 32
  24. 2024DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metricscited by 14
  25. 2024Dynamic Graph Information Bottleneckcited by 6
  26. 2023Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approachcited by 3
  27. 2025Preventing Rogue Agents Improves Multi-Agent Collaborationcited by 3
  28. 2024Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 29.

36 papers.

Sort:

By area:

  1. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 29
  2. 2025Building a Foundational Guardrail for General Agentic Systems via Synthetic Datacited by 29
  3. 2026The Attack and Defense Landscape of Agentic AI: A Comprehensive Surveycited by 28
  4. 2026A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypescited by 22
  5. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agentscited by 16
  6. 2026Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Taskscited by 7
  7. 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systemscited by 7
  8. 2026Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representationcited by 6
  9. 2026GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systemscited by 5
  10. 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systemscited by 5
  11. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directionscited by 4
  12. 2026GRADE: Graph Representation of LLM Agent Dependency and Executioncited by 4
24 more
  1. 2026Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placementcited by 4
  2. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  3. 2025The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systemscited by 3
  4. 2026Cross-Layer Semantic Flow Reconstruction for Attack Detection in Agentic Systemscited by 3
  5. 2026PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediationcited by 3
  6. 2026CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoringcited by 3
  7. 2026CatchBench: When Can an Agent Failure Be Caught?cited by 3
  8. 2025Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Developmentcited by 2
  9. 2026MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systemscited by 2
  10. 2026MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubricscited by 2
  11. 2026Beyond Fluency: Toward Reliable Trajectories in Agentic IRcited by 2
  12. 2026GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systemscited by 2
  13. 2025ORCA: ORchestrating Causal Agentcited by 1
  14. 2025Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspectivecited by 1
  15. 2026Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMscited by 1
  16. 2026SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systemscited by 1
  17. 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1
  18. 2026Agent System Operations: Categorization, Challenges, and Future Directionscited by 0
  19. 2026OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attackscited by 0
  20. 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivitycited by 0
  21. 2026Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learningcited by 0
  22. 2026Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modelingcited by 0
  23. 2026PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safetycited by 0
  24. 2026Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
  2. 2025Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
  3. 2025SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
  4. 2024NetSafe: Exploring the Topological Safety of Multi-agent Networks
  5. 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
  6. 2026When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
  7. 2026DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
  8. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination