mlsanityData to 14 Oct 2026

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

arXiv 2506.00509 ↗First posted 31 May 2025cs.CLcited by 8

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Large Language Model-based Multi-Agent Systems (MASs) have demonstrated strong advantages in addressing complex real-world tasks. However, due to the introduction of additional attack surfaces, MASs are particularly vulnerable to misinformation injection. To facilitate a deeper understanding of misinformation propagation dynamics within these systems, we introduce MisinfoTask, a novel dataset featuring complex, realistic tasks designed to evaluate MAS robustness against such threats. Building upon this, we propose ARGUS, a two-stage, training-free defense framework leveraging goal-aware reasoning for precise misinformation rectification within information flows. Our experiments demonstrate that in challenging misinformation scenarios, ARGUS exhibits significant efficacy across various injection attacks, achieving an average reduction in misinformation toxicity of approximately 28.17% and improving task success rates under attack by approximately 10.33%. Our code and dataset is available at: https://github.com/zhrli324/ARGUS.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 52 references that are in the map. First posted on arXiv 31 May 2025.

Builds on

27 of 52 references.

References · 27

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  8. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 548
  9. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agentscited by 538
  10. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  11. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  12. 2024Tool Learning with Large Language Models: A Surveycited by 223
15 more
  1. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  2. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  3. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 159
  4. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fastcited by 153
  5. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attackscited by 145
  6. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attackscited by 122
  7. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  8. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 86
  9. 2024Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplificationcited by 81
  10. 2025AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Managementcited by 38
  11. 2025Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategiescited by 16
  12. 2024Large Language Model Sentinel: LLM Agent for Adversarial Purificationcited by 10
  13. 2025Evaluating open-source Large Language Models for automated fact-checkingcited by 6
  14. 2024Fact-Level Confidence Calibration and Self-Correctioncited by 5
  15. 2025Multi-Agent Trustworthy Consensus under Random Dynamic Attackscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memorycited by 67
  2. 2025Aegis: Automated Error Generation and Attribution for Multi-Agent Systemscited by 22
  3. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  4. 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systemscited by 7
  5. 2026MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agentscited by 3
  6. 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1
  7. 2026Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Codecited by 0
  8. 2026Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Misinformation Propagation in Benign Multi-Agent Systems
  2. 2026Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification
  3. 2026ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
  4. 2026PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection
  5. 2026RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection
  6. 2026When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems
  7. 2025Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework
  8. 2025Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification