Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry
Abstract
Chemistry has recently entered a high-data regime as molecular databases from highthroughput platforms or computational studies have become available. Increasing automation within the chemical sciences leads to a more digital and precision chemistry. Dedicated scientific agents are becoming central to guiding the chemist through an ever-increasing amount of data and findings, including negative ones. Here, we introduce Magnolia, a persistent-memory artificial intelligence agent framework that integrates computational protocols, from docking to quantum chemistry, lab notebooks and chat logs relying on large language models (LLMs). It relies on a three-tier memory system: session-level observations are automatically captured and distilled into structured learnings, confirmed and elevated to project-tier entries and, when human-validated, promoted to cross-project rules that actively guide subsequent work and provide direct chemical feedback. We illustrate Magnolia on four case studies: quantum-chemical evaluation of aromatic systems (COMPAS database), molecular dynamics of butane and of modified DNA, and a protein–peptide docking campaign. Across these projects, Magnolia tracked 317 runs and accumulated 116 project-tier entries, from which four cross-project rules were promoted; in controlled replays of four tasks, runs with memory passed the checks that runs without it failed (for example, ten of ten docking-configuration checks, against one to four of ten). By combining automation, reproducibility, and human-in-the-loop control, our Magnolia framework streamlines docking, molecular dynamics and quantum chemistry calculations with direct analysis and LLM-augmented feedback, offering accelerated access to computational (bio)chemistry.
Related
- Computational identification of candidate biomarkers and compounds associated with skeletal muscle insulin sensitivity improvement mediated by physical activity: an integrative multi-omics and computational chemistry study.
- Essential Oils in Aromatic Plants: Chemistry, Isolation, Applications, Safety and Regulatory Framework
- A mechanobiological computational framework of intestinal healing for sutureless surgical strategies
- EquiDesign: a versatile computational framework for de novo protein sequence design.
- A computational super-resolution framework for multidimensional fluorescence imaging
BibTeX
@misc{jiang2026magnolia,
title = {{Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry}},
author = {Tao Jiang and Benjamin Navet and Yousouf Taghzouti and Fabien Gandon and Louis-Félix Nothias and Élise Dumont},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27230},
eprint = {2610.27230},
archivePrefix = {arXiv},
url = {https://univ-cotedazur.hal.science/hal-05830611v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry
AU - Tao Jiang
AU - Benjamin Navet
AU - Yousouf Taghzouti
AU - Fabien Gandon
AU - Louis-Félix Nothias
AU - Élise Dumont
PY - 2026
DA - 2026/10/19
PB - HAL
DO - 10.48550/arxiv.2610.27230
UR - https://univ-cotedazur.hal.science/hal-05830611v1
AB - Chemistry has recently entered a high-data regime as molecular databases from highthroughput platforms or computational studies have become available. Increasing automation within the chemical sciences leads to a more digital and precision chemistry. Dedicated scientific agents are becoming central to guiding the chemist through an ever-increasing amount of data and findings, including negative ones. Here, we introduce Magnolia, a persistent-memory artificial intelligence agent framework that integrates computational protocols, from docking to quantum chemistry, lab notebooks and chat logs relying on large language models (LLMs). It relies on a three-tier memory system: session-level observations are automatically captured and distilled into structured learnings, confirmed and elevated to project-tier entries and, when human-validated, promoted to cross-project rules that actively guide subsequent work and provide direct chemical feedback. We illustrate Magnolia on four case studies: quantum-chemical evaluation of aromatic systems (COMPAS database), molecular dynamics of butane and of modified DNA, and a protein–peptide docking campaign. Across these projects, Magnolia tracked 317 runs and accumulated 116 project-tier entries, from which four cross-project rules were promoted; in controlled replays of four tasks, runs with memory passed the checks that runs without it failed (for example, ten of ten docking-configuration checks, against one to four of ten). By combining automation, reproducibility, and human-in-the-loop control, our Magnolia framework streamlines docking, molecular dynamics and quantum chemistry calculations with direct analysis and LLM-augmented feedback, offering accelerated access to computational (bio)chemistry.
ER -