Large language models (LLMs) show promise for healthcare question answering, but clinical use is limited by weak verification, insufficient evidence grounding, and unreliable confidence signalling. We propose a multi-agent medical QA framework that combines complementary LLMs with evidence retrieval, uncertainty estimation, and bias checks to improve answer reliability. Our approach has two phases. First, we fine-tune three representative LLM families (GPT, LLaMA, and DeepSeek R1) on MedQuAD-derived medical QA data (20k+ question-answer pairs across multiple NIH domains) and benchmark generation quality. DeepSeek R1 achieves the strongest scores (ROUGE-1 0.536 +- 0.04; ROUGE-2 0.226 +-0.03; BLEU 0.098 -+ 0.018) and substantially outperforms the specialised biomedical baseline BioGPT in zero-shot evaluation. Second, we implement a modular multi-agent pipeline in which a Clinical Reasoning agent (fine-tuned LLaMA) produces structured explanations, an Evidence Retrieval agent queries PubMed to ground responses in recent literature, and a Refinement agent (DeepSeek R1) improves clarity and factual consistency; an optional human validation path is triggered for high-risk or high-uncertainty cases. Safety mechanisms include Monte Carlo dropout and perplexity-based uncertainty scoring, plus lexical and sentiment-based bias detection supported by LIME/SHAP-based analyses. In evaluation, the full system achieves 87% accuracy with relevance around 0.80, and evidence augmentation reduces uncertainty (perplexity 4.13) compared to base responses, with mean end-to-end latency of 36.5 seconds under the reported configuration. Overall, the results indicate that agent specialisation and verification layers can mitigate key single-model limitations and provide a practical, extensible design for evidence-based and bias-aware medical AI.

翻译：大语言模型在医疗问答领域展现出潜力，但其临床应用受限于验证能力薄弱、证据支撑不足以及置信度信号不可靠等问题。本文提出一种多智能体医疗问答框架，通过整合互补性大语言模型与证据检索、不确定性估计及偏误检测机制，以提升回答的可靠性。我们的方法包含两个阶段。首先，我们在基于MedQuAD衍生的医疗问答数据（涵盖美国国立卫生研究院多个领域的2万+问答对）上对三个代表性大语言模型家族（GPT、LLaMA和DeepSeek R1）进行微调，并基准测试其生成质量。DeepSeek R1取得了最优异的分数（ROUGE-1 0.536 ± 0.04；ROUGE-2 0.226 ± 0.03；BLEU 0.098 ± 0.018），并在零样本评估中显著优于专业生物医学基线模型BioGPT。其次，我们实现了一个模块化的多智能体流程：临床推理智能体（微调LLaMA）生成结构化解释，证据检索智能体查询PubMed以将回答锚定于最新文献，优化智能体（DeepSeek R1）提升清晰度与事实一致性；对于高风险或高不确定性案例，系统会触发可选的人工验证路径。安全机制包括蒙特卡洛Dropout和基于困惑度的不确定性评分，以及由LIME/SHAP分析支持的词汇与基于情感的偏误检测。在评估中，完整系统达到了87%的准确率，相关性约为0.80，且证据增强相较于基础回答降低了不确定性（困惑度4.13），在报告配置下平均端到端延迟为36.5秒。总体而言，结果表明智能体专业化与验证层能够缓解单一模型的关键局限，为循证与偏误感知的医疗AI提供了一个实用且可扩展的设计方案。