# Collective Hallucination in Multi-Agent LLMs:Modeling and Defense

arXiv: https://arxiv.org/abs/2606.07941 · HTML: https://mlsanity.com/paper/2606.07941/

## Key facts

- Cited by 5 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [Hallucination Detection in LLMs Using Spectral Features of Attention Maps](https://mlsanity.com/paper/2502.17598/) (2025)
- [Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective](https://mlsanity.com/paper/2411.14258/) (2024)
- [KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking](https://mlsanity.com/paper/2404.02935/) (2024)
- [Hallucination Detection in Large Language Models with Metamorphic Relations](https://mlsanity.com/paper/2502.15844/) (2025)
- [HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification](https://mlsanity.com/paper/2504.07069/) (2025)

## Built on by (most cited first, 5 of 5)

- [Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement](https://mlsanity.com/paper/2606.27409/) (2026)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [Reliability-Contagion Feasibility in LLM Multi-Agent Networks](https://mlsanity.com/paper/2607.21912/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)
- [PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs](https://mlsanity.com/paper/2610.10455/) (2026)

## 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.