Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). Existing solutions often rely on human intervention or underutilize the agent's ability to autonomously mitigate hallucination. To address these limitations, we draw inspiration from how humans make reliable decisions in the real world. They begin with introspective reasoning to reduce uncertainty and form an initial judgment, then rely on external verification from diverse perspectives to reach a final decision. Motivated by this cognitive paradigm, we propose InEx, a training-free, multi-agent framework designed to autonomously mitigate hallucination. InEx introduces internal introspective reasoning, guided by entropy-based uncertainty estimation, to improve the reliability of the decision agent's reasoning process. The agent first generates a response, which is then iteratively verified and refined through external cross-modal multi-agent collaboration with the editing agent and self-reflection agents, further enhancing reliability and mitigating hallucination. Extensive experiments show that InEx consistently outperforms existing methods, achieving 4%-27% gains on general and hallucination benchmarks, and demonstrating strong robustness.

翻译：幻觉仍是大型语言模型（LLMs）面临的关键挑战，阻碍了可靠多模态大型语言模型（MLLMs）的发展。现有解决方案常依赖人工干预，或未能充分利用智能体自主缓解幻觉的能力。为应对这些局限，我们借鉴人类在现实世界中做出可靠决策的方式：首先通过内省式推理降低不确定性并形成初步判断，随后借助多视角的外部验证达成最终决策。受此认知范式启发，我们提出InEx——一种无需训练的多智能体框架，旨在自主缓解幻觉。InEx引入基于熵的不确定性估计引导的内部内省推理，以提升决策智能体推理过程的可靠性。智能体首先生成响应，随后通过与编辑智能体及自反思智能体的外部跨模态多智能体协作进行迭代验证与优化，进一步增强可靠性并缓解幻觉。大量实验表明，InEx在通用基准与幻觉基准上均持续优于现有方法，取得4%-27%的性能提升，并展现出强大的鲁棒性。