发表机构
School of Mathematical and Computational Sciences; Massey University（数学与计算科学学院; 梅西大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出EAKR，在智能体管控系统MetaSynDec中实施后，可高效构建元分析所需的可执行分析知识表示，其性能优于直接大型语言模型生成，验证了相关方法的可行性与优势。
AI 中文摘要
元分析综合凸显了基于知识的科学分析中的一个根本挑战：结构化证据本身并不代表可执行计算所需的分析知识。在统计执行前，必须明确证据分配、分析对比、结局与时间点对齐、效应量公式化及方法可接受性等决策。现有自动化方法常将这些决策嵌入模型输出、生成的代码或工作流轨迹中，而非将其表示为可独立验证的知识。我们提出了可执行分析知识表示（EAKR），这是一种机器可操作的表示，用于将结构化证据转换为可执行元分析所需的知识。EAKR表示证据、关系、数值输入、约束、来源及未解决问题。我们在MetaSynDec中实施EAKR，这是一个智能体管控系统，其中大型语言模型提出结构化更新，确定性服务则基于模式和契约进行验证与执行。在58个综合单元中，MetaSynDec构建了所有EAKR，其中57个进入统计执行。在56个具备足够信息定义参考分析对象的单元中，38个（67.9%）实现了完整对象保真度，42个（75.0%）实现了精确证据集一致性，平均Jaccard相似度为0.909。生成的与已发表的置信区间在55个单元中的54个（98.2%）存在重叠。MetaSynDec在参考综合结构一致性（57/58对比23/58；p<0.001）方面优于直接大型语言模型生成，在23个共同完成的单元中，精确参考公式一致性（23/23对比1/23；p<0.001）也更优。这些发现提供了可行性证据，表明EAKR支持形式验证、可追溯性、统计执行，并相比直接大型语言模型生成提升了方法一致性。
英文摘要
Meta-analysis synthesis highlights a fundamental challenge in knowledge-based scientific analysis: structured evidence does not by itself represent the analytical knowledge required for executable computation. Decisions about evidence assignment, analytical contrasts, outcome and time-point alignment, effect-size formulation, and methodological admissibility must be explicit before statistical execution. Existing automated approaches often embed these decisions in model outputs, generated code, or workflow traces rather than representing them as independently verifiable knowledge. We introduce the Executable Analytical Knowledge Representation (EAKR), a machine-actionable representation of the knowledge required to transform structured evidence into executable meta-analysis. An EAKR represents evidence, relations, numerical inputs, constraints, provenance, and unresolved issues. We operationalise EAKR in MetaSynDec, an agentic harness in which large language models propose structured updates and deterministic services govern schema- and contract-based validation and execution. Across 58 synthesis units, MetaSynDec constructed all EAKRs, with 57 proceeding to statistical execution. Of 56 units with sufficient information to define a reference analysis object, 38 (67.9%) achieved complete object fidelity and 42 (75.0%) exact evidence-set agreement, with a mean Jaccard similarity of 0.909. Generated and published confidence intervals overlapped in 54 of 55 units (98.2%). MetaSynDec outperformed direct LLM generation in reference synthesis-structure agreement (57/58 versus 23/58; p<0.001) and among 23 jointly completed units, exact reference-formulation agreement (23/23 versus 1/23; p<0.001). These findings provide feasibility evidence that EAKR supports formal validation, traceability, statistical execution, and improved methodological agreement relative to direct LLM generation.
