Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents

Erdal Aydin; Yaman Arkun

math.OCOct 26, 2026

Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents

Authors: Erdal Aydin, Yaman Arkun

Organizations: School of Chemical Engineering, Aalto University, Espoo 02150, Finland · Department of Chemical and Biological Engineering, Koc University, 34450, Istanbul, Türkiye

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.

State Space Models

State space models represent sequences through evolving latent states, enabling efficient temporal modeling, system identification, and forecasting.

See all 299 papers

DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery
Aug 5, 2026Roberto Aliaga Medina, Paulina Quintanilla, Antonio del Rio ChanonaLarge Language Model-Guided Scientific Discovery Symbolic Regression
Department of Chemical Engineering Imperial College London South Kensington, London, SW7 2AZ, UK · Department of Chemical Engineering, Biotechnology, and Materials University of Chile, Santiago, Chile · Department of Chemical Engineering University College London Gower Street, London, WC1E 6BT, UK
Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
Jul 15, 2026David Krongauz, Arad Zulti, Eran Segal +1Dynamical Systems AI Agents for Scientific Discovery
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel · Department of Molecular Cell Biology, Weizmann Institute of Science, Rehovot, Israel · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates +2
LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
Oct 8, 2026Surya Shetty, Ulisses Braga-NetoAutonomous Scientific Discovery Autonomous Experimentation
Texas A&M University · Polara Labs Inc.

Aug 5, 2026J/K move · Enter open · S save

DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery

Roberto Aliaga Medina, Paulina Quintanilla, Antonio del Rio Chanona

Department of Chemical Engineering Imperial College London South Kensington, London, SW7 2AZ, UK · Department of Chemical Engineering, Biotechnology, and Materials University of Chile, Santiago, Chile · Department of Chemical Engineering University College London Gower Street, London, WC1E 6BT, UK

Large Language Model-Guided Scientific Discovery Symbolic Regression

Open paper AskPDF arXiv

Kinetic model discovery is a central challenge in chemical engineering, as accurate rate expressions are essential for understanding and controlling chemical and biological processes. Symbolic regression (SR) has emerged as a powerful data-driven approach for identifying interpretable kinetic models, but usually operates without domain knowledge, often exploring physicochemically implausible models. Large language models (LLMs) offer a promising avenue for injecting domain expertise into this search. Here, we introduce an LLM-guided SR framework, embedding an LLM module within an iterative SR algorithm for automated kinetic model discovery. The LLM performs two roles at each iteration: (1) a qualitative physicochemical critique of the best SR candidates, and (2) the proposal of new candidate rate expressions guided by the SR-generated models and embedded chemical knowledge. Our framework is evaluated on four in silico case studies of increasing complexity, spanning heterogeneous catalysis and bioprocess systems. Results show the LLM-guided framework reduces iterations to identify the ground-truth model by

41.7-79.3\%

versus a state-of-the-art SR framework, with the LLM directly proposing the correct model structure in over half of the guided runs. In practical settings, where each iteration typically requires a new wet-lab experiment, this translates into a substantial reduction in experimental effort. Predictive performance on an independent validation set is equivalent between both approaches, with

R^2>0.98

in all case studies. Ablation studies indicate that both the SR component and the LLM scale contribute to this performance, with a reduced-size LLM largely retaining discovery efficiency. These findings demonstrate that LLMs can effectively inject domain knowledge into scientific model discovery, paving the way toward fully automated, domain-aware kinetic modelling pipelines.

Abstract

State Space Models

Explore similar work

DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery

Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System

LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models