Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with five state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, GPT-oss-20B) on three benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model chain-of-thought reasoning and chain-of-thought-based majority voting. Results: Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains. Conclusion: The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.

翻译：目的：增强大型语言模型在医学问答任务中的准确性、可解释性和鲁棒性。方法：我们设计了一种多智能体同行评审推理方法，其中多个LLM智能体独立生成链式推理与候选答案，随后充当同行评审员对彼此的推理进行事实正确性和逻辑严谨性评估，并选择评分最高的推理链生成最终答案。实验采用五个最先进的LLM（Llama-3.1-8B、Qwen2.5-7B、Phi-4、DeepSeek-LLM-7B、GPT-oss-20B）在三个基准数据集（HeadQA、MedQA-USMLE、PubMedQA）上进行，并与单模型链式推理及基于链式推理的多数投票方法进行性能对比。结果：同行评审推理方法持续优于两种基线方法。最佳模型组合在三个数据集上平均准确率达0.820，超过最强单模型（0.777）和多数投票集成方法（最高0.789）。该方法随着参与模型数量增加而有效扩展，同时同行评审能可靠区分高质量与低质量推理链。结论：所提出的多智能体同行评审推理方法使LLM既充当求解者又担任评估者，在医学问答任务中展现出优越性能。通过强调推理质量而非单纯答案一致性，该方法提升了准确性、可解释性和鲁棒性，为构建可信赖的生物医学AI系统提供了有前景的方向。