LLM 驱动智能体实现生物过程动力学与速率的自主结构发现
Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents
AI 导读
一篇 arXiv 论文提出由 LLM 智能体驱动的混合闭环架构，用于连续生物制造中动力学状态空间的自主发现。该框架基于两级 RAG 库，结合 Moving Horizon Estimation 与对数分解，把细胞生长动力学解耦为乘性（抑制）与加性（调控）残差通道，并在统计退化时由主动实验设计（DoE）控制器触发定向扰动。
正文 · 原文
Abstract:High-fidelity digital twins in continuous biomanufacturing are often bottlenecked by incomplete kinetic models, while standard data-driven algorithms (e.g., SINDy, PINNs) lack interpretability or impose rigid physical assumptions. This paper introduces a hybrid closed-loop architecture for autonomous kinetic state-space discovery driven by a Large Language Model (LLM) agent. The framework employs a sequential "isolation-peeling" methodology across orthogonal operational regimes. This algorithmic peeling mathematically decouples entangled multiplicative (inhibitory) and additive (catalytic) biological rate law. Grounded in a Two-Level Retrieval-Augmented Generation (RAG) library, the framework utilizes Moving Horizon Estimation (MHE) and logarithmic decomposition to decouple complex cell growth kinetics into orthogonal multiplicative (inhibitory) and additive (regulatory) residual channels. When statistical degeneracy occurs an Active Design of Experiments (DoE) controller dynamically triggers targeted perturbations to decorrelate competing model hypotheses. Evaluated on a continuous stirred-tank reactor exhibiting unmodeled Haldane inhibition, Luong product toxicity, and secondary metabolite autocatalysis, the framework autonomously expanded the state space and recovered ground-truth parameters with under 6% error without a priori kinetic knowledge.
| Subjects: | Optimization and Control (math.OC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35391 [math.OC] |
| (or arXiv:2610.35391v1 [math.OC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35391 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Erdal Aydin Dr. [view email]
[v1]
Mon, 26 Oct 2026 13:10:07 UTC (1,605 KB)
来源：arXiv cs.AI · arxiv.org