发表机构
Weizmann Institute of Science; Mohamed bin Zayed University of Artificial Intelligence; University of Haifa; Jonkoping University（魏茨曼科学研究所; 穆罕默德·本·扎耶德人工智能大学; 海法大学; 延雪平大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究旨在用大语言模型驱动智能体系统自动发现生物系统常微分方程。提出MEDA系统，能检索知识、定义变量、生成约束等。通过多种任务评估，该系统可恢复正确变量，实现结构恢复，生成合理模型，还明确关键组成部分。
AI 中文摘要
自动科学发现长期以来一直是计算学者的目标，即让机器能自主发现自然秘密，使计算系统超越数据拟合工具，朝着生成和完善宇宙机制模型发展。符号回归（SR）和基于大语言模型（LLM）的智能体的进展表明此类系统可从数据中恢复方程、纳入领域先验并自动化部分研究工作流程。但现有方法多聚焦于狭义方程发现基准或广义端到端自动化管道，生物系统研究较少。本文介绍MEDA系统，这是一个由LLM和SR驱动的智能体框架，用于发现生物及受生物启发的动力系统的常微分方程（ODE）模型。MEDA可检索背景知识、定义允许变量、生成机制约束、提出候选ODE并进行拟合和评估。我们在有无实验数据的情况下，通过典型模型检索、基于推理的对未见变体的外推以及开放式发现等任务对其进行评估。在这些设置中，MEDA恢复了正确的状态变量，在检索和外推任务中实现了强大的结构恢复，并生成了具有生物学合理性的面向发现的模型。消融和鲁棒性分析表明，知识引导的形式化和机制约束是关键组成部分，仅数值拟合可能保留轨迹兼容但生物学上错误的方程。
英文摘要
Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.
