mlsanityData to 14 Oct 2026

Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning

arXiv 2505.16557 ↗First posted 22 May 2025cs.MAcited by 15

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

Abstract (arXiv)

The rise of Large Language Model-based Multi-Agent Planning has leveraged advanced frameworks to enable autonomous and collaborative task execution. Some systems rely on platforms like review sites and social media, which are prone to fraudulent information, such as fake reviews or misleading descriptions. This reliance poses risks, potentially causing financial losses and harming user experiences. To evaluate the risk of planning systems in real-world applications, we introduce WandaPlan, an evaluation environment mirroring real-world data and injected with deceptive content. We assess system performance across three fraud cases: Misinformation Fraud, Team-Coordinated Multi-Person Fraud, and Level-Escalating Multi-Round Fraud. We reveal significant weaknesses in existing frameworks that prioritize task efficiency over data authenticity. At the same time, we validate WandaPlan's generalizability, capable of assessing the risks of real-world open-source planning frameworks. To mitigate the risk of fraud, we propose integrating an anti-fraud agent, providing a solution for reliable planning.

Key facts. Cited by 15 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 21 of its 54 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

21 of 54 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agents19 Dec

Other references · 20

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  4. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  5. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  6. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  7. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  8. 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 246
  9. 2023DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Textcited by 210
  10. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  11. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  12. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
8 more
  1. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  2. 2024From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake Newscited by 51
  3. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  4. 2024LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planningcited by 45
  5. 2024TravelAgent: An AI Assistant for Personalized Travel Planningcited by 39
  6. 2024Robust Planning with LLM-Modulo Framework: Case Study in Travel Planningcited by 34
  7. 2025Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducementscited by 32
  8. 2024Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an "AI Therapist"cited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 5.

15 papers.

Sort:

By area:

  1. 2025Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Modelscited by 16
  2. 2025The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Marketscited by 15
  3. 2026AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitorcited by 10
  4. 2026Predicting LLM Output Length via Entropy-Guided Representationscited by 9
  5. 2025When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platformscited by 8
  6. 2025COMPKE: Complex Question Answering under Knowledge Editingcited by 6
  7. 2025Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Modelscited by 6
  8. 2025Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMscited by 6
  9. 2026LLM Agents in Law: Taxonomy, Applications, and Challengescited by 5
  10. 2025Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localizationcited by 4
  11. 2025The Compositional Architecture of Regret in Large Language Modelscited by 3
  12. 2025SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Managementcited by 1
3 more
  1. 2025HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debatecited by 1
  2. 2026Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMscited by 0
  3. 2026AISPA: User-Centric System Prompt Auditing for Large Language Model Applicationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems
  2. 2026Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
  3. 2026SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
  4. 2024Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs
  5. 2025Analyzing Information Sharing and Coordination in Multi-Agent Planning
  6. 2026DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
  7. 2026SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection
  8. 2026LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios