Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry

Tao Jiang; Benjamin Navet; Yousouf Taghzouti; Fabien Gandon; Louis-Félix Nothias; Élise Dumont

cs.AIOct 19, 2026

Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry

Authors: Tao Jiang, Benjamin Navet, Yousouf Taghzouti, Fabien Gandon, Louis-Félix Nothias, Élise Dumont

Organizations: Université Côte d’Azur, CNRS, ICN, Nice, France · Inria, Université Côte d’Azur, CNRS, I3S, France

Abstract

Chemistry has recently entered a high-data regime as molecular databases from high-throughput 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.

Figures & tables

Figure 1: System architecture. The researcher interacts in natural language with the OpenCode agent, which communicates with two MCP servers ( compchem-tools and compchem-memory ), using stdio for memory and streamable HTTP for the tool service. Tools dispatch jobs to the local machine (light jobs) or to a remote HPC cluster ( ssh-slurm ); every run is registered in the memory run history. The LLM provider, local or API-based, serves both agent reasoning and memory distillation.

Figure 2: Memory architecture. The three-tier promotion ladder: session ( staging/ ) $\rightarrow$ project ( entries/ ) $\rightarrow$ reviewed (operational rules in rules/ load at every session start; task-shaped skills in skills/ are retrieved by task relevance), fed by chat-session distillation, with an implemented self-reflex consolidation loop that merges duplicate findings (human-reviewed, Git-reversible); rule-elevation proposals are generated automatically but applied only on human confirmation.

Molecule	IE ${}_{\text{exp}}$	$-$ E(HOMO) xTB	$-$ E(HOMO) B3LYP	Adiabatic IP
benzene	9.244	10.95	6.88	9.00
naphthalene	8.144	10.27	5.95	7.73
phenanthrene	7.891	10.22	5.89	7.45
triphenylene	7.870	10.31	6.01	7.43
chrysene	7.600	10.04	5.68	7.09
benz[a]anthracene	7.450	9.91	5.48	6.90

Table 1: Experimental vs. calculated IPs (NIST Chemistry WebBook, first column) vs. computed: xTB, B3LYP and adiabatic IP with the

\Delta

SCF approach. All values are given in eV.

Figure 3: Quantum-chemistry benchmark on the COMPAS subset. (a) HOMO–LUMO gaps by ring count for the 179 cata-condensed PAHs, GFN2-xTB versus B3LYP/def2-SVP. (b) Computed versus experimental ionization energies (NIST Chemistry WebBook); the dashed line is the identity. (c) Vertical singlet–triplet gaps by method, computed at GFN2-xTB geometries. (d) AIMNet2-NSE versus GFN2-xTB vertical triplet gaps.

Figure 4: Magnolia’s automated analysis of the classical vs. AIMD molecular trajectories for butane, of respectively 10 ns and 50 ps. The AIQM2 torsion vs. time is magnified for visualization purposes.

Panel of Figure 5 — Figure 5: a) Sequence of a series of six ( $n$ =0…5) double-stranded sequences featuring DX=5-carboxycytosine-containing or DX=5-carboxyuracil-containing. The composition of the simulation boxes is given as ESI. b) DSSR analysis for sequences 1: RMSD, bend, opening and propeller over time.

Figure 6: Protein–peptide docking. (a) AIR-free scores on the initial full-length receptor under literature-defined versus predicted-pocket restraints; the apparent improvement under predicted pockets was later shown to reflect docking against the wrong site. (b) AIR-free scores on the corrected protocol (full-length receptor, crystal-contact restraints): the literature-derived 9-mer, the shortened 7-mer, and single-residue variants. Best-defined (highest-DockQ) cluster per run; peptide identities withheld; DockQ is self-referential (cluster tightness, not accuracy against a reference complex).

Store	Tracked runs	Tier 1	Tier 2	Tier 3
Quantum-chemistry benchmark (CS1)	0	7	0	0
Butane MD (CS2)	6	8	0	0
Modified-DNA MD (CS3)	116	12	7	0
Docking campaign (CS4), June–July store	178	381	85	4
Docking campaign (CS4), earlier pilot store	17	3	24	0
Total	317	411	116	4

Table 2: Project stores of the four case studies at the snapshot of 2026-09-02. Runs are lifecycle records dated up to the snapshot; staging and project-tier counts are read from the versioned store histories (index files excluded). Case Study 1’s benchmark ran as shell-script batches outside the lifecycle manager; it therefore has no run records. The docking campaign comprises two stores, listed separately; the June–July store is the one analyzed in Figure 7 . Promoted rules are learnings elevated from entries into durable, human-gated rules.

Type	Count	Example title
Scientific finding	23	“P2Rank restraints protocol yields superior scoring over experimental site restraints”
General observation / correction	40	“Mutations are NOT additive: a single-residue variant shifts the binding mode and proves context-dependence”
Failure pattern	14	“cmrest blind docking unreliable: 30+ point variation from input conformation bias”
Error resolution	16	“Template-built peptide PDBs have garbage geometry from hardcoded offsets”
Parameter guidance	13	“Always use max walltime for cpucourt partition (72h)”
Success pattern	10	“N-terminal ALA extension outperforms C-terminal: $+16$ AIR-free vs parent”

Table 3: Project-tier entry inventory by type.

Figure 7: Learning-type mix (a) and cumulative entries by learning type (b) across all entries (staging and confirmed) of the docking campaign’s June–July store (466 entries at the snapshot of 2026-09-02; Table 2 ). Entries are plotted in chronological order in bins of 50: nine complete bins span 2026-06-01 to 2026-07-14; a tenth, partial bin holds the 16 remaining records (all staging, dated 2026-07-14 to 2026-08-18), so all 466 records are plotted. Panel (b) gives the same record as cumulative absolute counts on the same entry-ordinal axis. Error and failure entries are split into operational (tool, infrastructure, process) and scientific negative results (falsified hypotheses, failing mutations, method limitations) using keyword rules with manual review of every title, and the operational entries carry the class tags tabulated in ESI Table 8 . The remaining colour groups combine the other recorded types: parameter guidance with workflow notes, scientific findings with success patterns, and other notes, observations and decisions.

Task	ds	kimi	ds	kimi	ds	kimi
	Memory off		Memory on		Oracle
Docking-configuration recall (10 checks)	1, 4	4, 4	10, 10	10, 10	10, 10	10, 10
Covalent-docking protocol recall (13 items)	1, 1	0, 1, 1	13, 13	12, 12	13, 13	13, 13
Warhead production conventions (2 runs per cell)	0/2	0/2	2/2	2/2	2/2	2/2
Flexible-residue range (1 value per run)	0/5	1/3	3/3	2/2	3/3	2/2

Table 4: Controlled replay by model (ds = DeepSeek v4.1-flash, kimi = Kimi K2.7; two or more runs per model per condition). Rows 1 and 4 concern HADDOCK3 docking; rows 2 and 3 concern covalent docking with Gnina. Rows 1–2 list each run’s score out of the graded total: for example, the two ds memory-off docking-configuration runs scored 1 and 4 of the 10 checks, while all four memory-on runs scored 10 of 10. Rows 3–4 report runs that met the task criterion out of runs attempted, since there the run is the smallest unit that can pass; attempts include runs that stopped without producing an answer (four in the ds flexible-range condition), counted as failures. The oracle runs received the decisive facts in the prompt.

Operation	Measurement
Session boot (scan, handover merge, context)	34–109 s, dominated by the store scan and the handover merge
Memory retrieval ( memory_get_context )	8–13 s; over 90% in two model calls (re-ranking); local scoring 50–700 ms
Distillation call	1–6 s per call (small model)
Model volume for memory maintenance	$\sim$ 1.6 M tokens in one month (about 2,900 calls), busiest project
Store size, session logs included	below 20 MB (largest project); boot context below 35 KB
Replay run cost	$0.0005–$ 0.034 per run, flash-tier API pricing

Table 5: Operational measurements at the scale exercised so far (late September 2026). Boot and retrieval combine the controlled-replay sandbox and the busiest live project. The replay cost is the per-run model spend; the second model used in the replay runs on a subscription plan and is not billed per token.

Figure 8: Chemical structures of the 179 compounds extracted from the COMPAS database with seven or less rings.

System	bp	atoms	OPC waters	Na +	Cl -	$V$ / Å 3	edge / Å
5-CAC
XCD seq1	20	51606	12564	58	20	442198	95.0
XCD seq2	22	73254	17943	62	20	616951	106.3
XCD seq3	24	73010	17849	66	20	617316	106.3
XCD seq4	26	88414	21667	70	20	741914	113.1
XCD seq5	28	111330	27363	74	20	922901	121.7

Table 6: Composition of the 12 simulated duplexes containing 5-carboxycytosine (XCD) or 5-carboxycytosine (X5D), and characteristics of solvation in truncated octahedral water OPC boxes, with a cut-off of 10 Å. Seq n differ by the number – see Figure 5, main text.

Stage	Ensemble	Length	Restraints	Thermostat / Barostat	Output
			(kcal mol -1 Å -2 )
min1	—	5000 cycles	500	—	every 50 steps
min2	—	5000 cycles	none	—	every 50 steps
heat	NVT	100 ps	10	Langevin ( $\gamma=2$ ps -1 ),	1 ps coords,
	( ntb=1 )	(50 000 steps)		linear 0 $\to$ 300 K; ntx=1 , irest=0	10 ps restart
equil	NPT	100 ps	2	300 K, 1 atm

Table 7: Steps constituting our MD protocol (Amber 26 sander ;

\Delta t=2

fs; SHAKE was applied on bonds featuring hydrogens, ntc=2 / ntf=2 ; 10 Å cutoff with PME; iwrap=1 ). Restraints are positional on all atoms of the DNA (Amber mask :1--2N ). Minimization steps were decomposed into 2500 steps of steepest descent followed by 2500 steps of conjugate gradients.

Class	Entries	First	Last	Promoted rule	After rule
cluster-trust	4	06-01	06-18	–	–
oom	4	06-01	06-01	06-01	0
output-collision	6	06-01	06-16	–	–
p2rank	2	06-01	06-01	–	–
tooling	6	06-01	06-17	–	–
transfer	17	06-01	07-13	–	–

Table 8: Operational error and failure classes in the docking campaign store (all tiers; snapshot 2026-09-02). The 103 entries resolve into 28 classes by keyword rules with manual review. “Entries” counts recorded events; “first” and “last” are the dates (year 2026) of the first and last recorded event. Rule dates mark the four promoted classes; “after rule” counts events strictly after the promotion date (0 for all four; events on the rule date itself are not counted there). Single-entry classes never recurred.

AI Agents for Scientific Discovery

AI agents for scientific discovery use language models, tools, and experiments to generate, test, and refine scientific knowledge.

See all 288 papers

From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
Oct 5, 2026Pierre Llompart, Levent Guner, Helen Lai +2AI Agents for Scientific Discovery LLM Agent Orchestration
AMD Silo AI, Stockholm, Sweden · Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK · Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden +1
Molecular LLM Agents: From Architectural Design to Scientific Autonomy
Aug 24, 2026Jiatong Li, Wengyu Zhang, Weida Wang +8LLM Agents AI Agents for Scientific Discovery
The Hong Kong Polytechnic University Hong Kong, China · Shanghai AI Lab Shanghai, China · National University of Singapore Singapore +1
Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
Aug 19, 2026Pavlo O. Dral, Hassan Nawaz, Arif UllahAI Agents for Scientific Discovery Computational Quantum Chemistry
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, Xiamen University, Xiamen, Fujian 361005, China · Institute of Physics, Faculty of Physics, Astronomy, and Informatics, Nicolaus Copernicus University in Toruń, ul. Grudziadzka 5, 87-100 Toruń, Poland · Institute of Advanced Studies, Nicolaus Copernicus University in Toruń, ul. Wileńska 4, 87-100 Toruń, Poland +2

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

From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?

Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo+1

AMD Silo AI, Stockholm, Sweden · Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK · Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden+1

AI Agents for Scientific Discovery LLM Agent Orchestration Molecular Generation Drug Discovery

Open paper AskPDF arXiv

Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to discriminate agentic proposals from held-out compounds, and judged the SAR reasoning broadly plausible yet incomplete. Together, these results position MAGI as a coordination layer pluggable into existing computational chemistry workflows. The ceiling on real projects, however, remains currently set by scorer applicability rather than by tool orchestration.

Abstract

AI Agents for Scientific Discovery

Explore similar work

From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?

Molecular LLM Agents: From Architectural Design to Scientific Autonomy

Science Done on a Machine by a Machine: AI Agents in Computational Chemistry