MedVerse: 通过DAG结构并行执行实现高效可靠的医学推理
MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
AI总结：
MedVerse通过将医学推理转化为可并行的有向无环图过程，提升复杂医疗问题的效率和可靠性，实验表明其在通用大语言模型上提升了8.9%的性能，同时减少推理延迟并提高生成吞吐量。
摘要：
大型语言模型（LLMs）在广泛的医学推理任务中表现出强大的性能和快速的进步。然而，其顺序自回归解码强制将本质上并行的临床推理，如鉴别诊断，限制为单一线性推理路径，从而限制了复杂医疗问题的效率和可靠性。为此，我们提出MedVerse，一种用于复杂医学推断的推理框架，基于Petri网理论将医学推理重新表述为可并行的有向无环图（DAG）过程。该框架采用跨数据、模型架构和系统执行的全栈设计。在数据创建方面，我们引入了MedVerse Curator，一个自动化管道，将知识导向的医学推理路径合成并转换为Petri网结构的表示。在架构层面，我们提出了一种拓扑感知的注意力机制，具有自适应位置索引，支持并行推理同时保持逻辑一致性。系统层面，我们开发了定制的推断引擎，支持并行执行而无需额外开销。实验评估显示，MedVerse在通用大语言模型上提升了高达8.9%。与专门化的医学LLMs相比，MedVerse在性能上具有可比性，同时通过其并行解码能力实现了1.3倍的推理延迟减少和1.7倍的生成吞吐量增加。代码可在https://github.com/aiming-lab/MedVerse上获得。
英文摘要：
Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequential autoregressive decoding forces inherently parallel clinical reasoning, such as differential diagnosis, into a single linear reasoning path, limiting both efficiency and reliability for complex medical problems. To address this, we propose MedVerse, a reasoning framework for complex medical inference that reformulates medical reasoning as a parallelizable directed acyclic graph (DAG) process based on Petri net theory. The framework adopts a full-stack design across data, model architecture, and system execution. For data creation, we introduce the MedVerse Curator, an automated pipeline that synthesizes knowledge-grounded medical reasoning paths and transforms them into Petri net-structured representations. At the architectural level, we propose a topology-aware attention mechanism with adaptive position indices that supports parallel reasoning while preserving logical consistency. Systematically, we develop a customized inference engine that supports parallel execution without additional overhead. Empirical evaluations show that MedVerse improves strong general-purpose LLMs by up to 8.9%. Compared to specialized medical LLMs, MedVerse achieves comparable performance while delivering a 1.3x reduction in inference latency and a 1.7x increase in generation throughput, enabled by its parallel decoding capability. Code is available at https://github.com/aiming-lab/MedVerse.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
