mlsanityData to 7 Oct 2026

Collective Hallucination in Multi-Agent LLMs:Modeling and Defense

arXiv 2606.07941 ↗First posted 6 Jun 2026cs.CRcited by 5

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Hallucination is a critical reliability challenge in multi-agent Large Language Model (LLM) systems because unsupported claims can propagate through recursive interactions and produce collective false consensus. We model collective hallucination as a time-evolving network process over directed communication graphs and introduce HPR-Adaptive, a defense framework combining dynamic trust weighting, external claim verification, propagation-aware interaction regulation, and selective isolation of unreliable agents. We evaluate HPR-Adaptive on 1,317 TruthfulQA and TriviaQA queries using a heterogeneous six-agent system across five recursive reasoning rounds and multiple communication topologies. Compared with undefended multi-agent reasoning, HPR-Adaptive reduces hallucination rate from 0.118 to 0.072 (39.0%), while increasing factual accuracy from 0.812 to 0.867 and semantic consistency from 0.784 to 0.836. It also lowers the hallucination amplification factor from 1.34 to 1.08, increases propagation resistance from 0.882 to 0.928, and reduces the effective reproduction number from 1.08 to 0.81, shifting the system from self-sustaining propagation to controlled attenuation. Scale-free networks show the strongest cascading behavior without defense, with an amplification factor of 1.45 and reproduction number of 1.21; HPR-Adaptive reduces these to 1.12 and 0.92, respectively. These results show that propagation-aware control can substantially improve the factual reliability and stability of recursive multi-agent LLM systems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 16 of its 29 references that are in the map. First posted on arXiv 6 Jun 2026.

Builds on

16 of 29 references.

References · 16

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  11. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  12. 2025Hallucination Detection in LLMs Using Spectral Features of Attention Mapscited by 42
4 more
  1. 2024Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspectivecited by 29
  2. 2024KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checkingcited by 26
  3. 2025Hallucination Detection in Large Language Models with Metamorphic Relationscited by 24
  4. 2025HalluciNot: Hallucination Detection Through Context and Common Knowledge Verificationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placementcited by 4
  2. 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1
  3. 2026Reliability-Contagion Feasibility in LLM Multi-Agent Networkscited by 0
  4. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0
  5. 2026PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems
  2. 2026MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
  3. 2024Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
  4. 2026Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems
  5. 2024Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models
  6. 2025Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
  7. 2026Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
  8. 2025InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration