Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents
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.
Related
- GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
- SiteEvo: An LLM Agent for Autonomous Discovery of Site-Adaptive Massive MIMO Detectors
- Large-Scale Autonomous Discovery of Kissing Number Constructions
- Non-autonomous dynamics of inner functions: mixing and entropy
- Autonomous self-harmonic drift in Langevin dynamics causes a compaction of underlying domain for the density of Stochastic Localization
BibTeX
@misc{aydin2026autonomous,
title = {{Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents}},
author = {Erdal Aydin and Yaman Arkun},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35391},
eprint = {2610.35391},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35391},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents
AU - Erdal Aydin
AU - Yaman Arkun
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35391
UR - https://arxiv.org/abs/2610.35391
AB - 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.
ER -