cs.AIOct 20, 2026

RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials

Authors: Marko Petković, Susanne Gooijer, José Manuel Vicent-Luna, Vlado Menkovski, Sofía Calero

Organizations: Department of Applied Physics and Science Education, Eindhoven University of Technology, Eindhoven, The Netherlands · Eindhoven Artificial Intelligence Systems Institute (EAISI), Eindhoven University of Technology, Eindhoven, The Netherlands · Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, The Netherlands

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Porous-material adsorption studies require coordinated structure preparation, force-field selection, simulation, validation, and interpretation, making end-to-end automation difficult. We test whether RaspAssistant, a hierarchical multi-agent framework, can carry an adsorption study from force-field preparation through validation and downstream separation analysis. Across twelve multi-agent workflow-reproduction runs spanning four adsorption and separation benchmarks, overall scores ranged from 8.50 to 10.00 on a rubric evaluating workflow correctness, simulation validity, and analysis consistency. In a separate eight-case force-field extraction benchmark, the mean weighted score was 0.967, combining parameter agreement and RASPA readiness. In open-ended studies, the system diagnosed and refined an acetylene force field and, after validating a CO2_2 force field against MFI experiments, screened 197 pure-silica zeolites that passed automated input checks. These results demonstrate autonomous workflow execution after task specification and input provision: RaspAssistant coordinates, validates, adapts, and documents extended adsorption-simulation workflows while exposing model sensitivity and methodological limitations for expert review.

Figures & tables

Figure 1: Agent architecture of RaspAssistant. Orange nodes denote higher-level agents responsible for planning, coordination, and verification, while blue nodes denote lower-level ReAct agents that alternate reasoning with tool actions. The red dashed subsystem supports literature search, force field extraction, adaptation, and parameter file generation. The blue dashed subsystem supports simulation setup, execution, analysis, plotting, and force field fitting for workflow reproduction. Shared databases, examples, memories, and tools occupy the bottom layer. Agent roles are listed in Table S5 .
BenchmarkRunOverall (/10)Elapsed (d)Tokens (M)Cost (US$)
TAMOF-1110.008.81215
 29.602.41214
 39.608.878
Acetylene19.0560.0 *2117
 29.605.01415
 38.7336.31111
Table 1: Scores and approximate resource use for the twelve multi-agent workflow-reproduction runs.
MethodIoUReadinessSFFS_{\mathrm{FF}}Cost ($)
CO 2 EPM2 410.95100%0.9700.19
CO 2 in zeolites 421.0088%0.9520.23
CO 2 in zeolites 430.9992%0.9620.34
CO 2 , N 2 , O 2 , Ar in zeolites 440.98100%0.9880.24
TraPPE-zeo 451.00100%1.0000.15
C x H x , CO 2 , N 2 , O 2 in zeolites 461.00100%1.0000.65
Table 2: Force-field extraction performance and weighted score by source.
Figure 2: Schematic overview of Case Study 1. Here, baseline validation means validation of the supplied initial force field. The workflow includes detection of the poor C 2 H 2 isotherm in Fe-MOF-74, convergence checks, force field fitting, validation of the fitted model, and subsequent mixture adsorption and adsorption site analysis.
Figure 3: C 2 H 2 adsorption isotherms in Fe-MOF-74. “Baseline simulation” uses the initial force field. “Revalidation simulation” uses the fitted force field. The plot was generated by RaspAssistant. The isotherm from Ref. 38 was added manually for comparison.
ModelMean Fe–C distance (Å)
Initial force field3.12
RaspAssistant fitted force field2.63
Literature force field2.60
Experiment2.50
Table 3: Comparison of the arithmetic mean of the two Fe–C contacts for C 2 H 2 adsorbed in Fe-MOF-74.
  AgentLiterature
Interaction PairAtom Typesϵ\epsilon (K)σ\sigma (Å)ϵ\epsilon (K)σ\sigma (Å)
Metal siteFe – C C2H2{}_{\mathrm{C_{2}H_{2}}}680.02.35538.922.878
Framework oxygenO1 – C C2H2{}_{\mathrm{C_{2}H_{2}}}10.02.90079.232.870
 O2 – C C2H2{}_{\mathrm{C_{2}H_{2}}}20.03.05079.232.870
 O3 – C C2H2{}_{\mathrm{C_{2}H_{2}}}20.03.05079.232.870
Framework carbonC1/2/3/4 – C C2H2{}_{\mathrm{C_{2}H_{2}}}——78.963.055
Table 4: Comparison of fitted Lennard–Jones parameters for acetylene–framework interactions in Fe-MOF-74. Literature parameters are taken from Ref. 38 .
Figure 4: Comparison of C 2 H 2 /CH 4 (a) and C 2 H 2 /CO 2 (b) mixture selectivities from the fitted Fe-MOF-74 and retained IRMOF-1 models with Ref. 38 . RaspAssistant generated the plot. Reference data were added manually.
Figure 5: Normalized minimum periodic interaction-site-to-Fe distance distributions in Fe-MOF-74 for equimolar C 2 H 2 /CH 4 and C 2 H 2 /CO 2 mixtures at 298 K and 1000 kPa. The sharp short distance peak for C 2 H 2 indicates preferential localization near the open Fe sites, whereas CO 2 and CH 4 are mainly distributed farther away in the pore space.
Figure 6: Schematic overview of the main steps taken by RaspAssistant in Case Study 2. The workflow includes preparation of literature-based force-field candidates, validation against MFI CO 2 adsorption experiments, selection of the best-performing force field, 298 K screening of the pure-silica zeolite dataset, and post-processing through ranking and descriptor analysis.
Figure 7: Validation of the candidate force fields against the provided CO 2 adsorption isotherm in MFI at 303 K. The TraPPE_Silica_2016 candidate combines TraPPE CO 2 with a Vujic-derived silica-zeolite model and gives the best agreement. Open markers flag block-drift outliers. These points are retained in the error calculations (see the SI).
Figure 8: Distribution of interpolated CO 2 uptake at 1, 10, and 100 kPa and of the derived 1–100 kPa working capacity in Case Study 2.
Figure 9: Relationship between framework density and simulated CO 2 uptake at 1 kPa for the screened pure-silica zeolites. Highlighted topologies correspond to positive outliers relative to the overall linear trend, indicating unusually high uptake for their framework density.
RunWorkflowSimulationsAnalysisOverall
Run 110.0010.0010.0010.00
Run 210.009.0010.009.60
Run 310.009.259.509.60
Multi-agent average10.009.429.839.73
Single-agent baseline9.139.138.759.05
Table S1 : Multi-agent RaspAssistant performance and the single-agent baseline on Study 1.
RunWorkflowSimulationsAnalysisOverall
Run 19.508.1310.009.05
Run 210.009.0010.009.60
Run 38.888.568.758.73
Multi-agent average9.468.569.589.13
Single-agent baseline7.508.568.138.05
Table S2 : Multi-agent RaspAssistant performance and the single-agent baseline on Study 2.
RunWorkflowSimulationsAnalysisOverall
Run 18.698.758.008.58
Run 29.509.759.509.60
Run 38.508.508.508.50
Multi-agent average8.909.008.678.89
Single-agent baseline6.887.255.636.78
Table S3 : Multi-agent RaspAssistant performance and the single-agent baseline on Study 3.
RunWorkflowSimulationsAnalysisOverall
Run 19.508.508.758.95
Run 29.008.318.758.68
Run 38.759.257.508.70
Multi-agent average9.088.698.338.78
Single-agent baseline9.388.635.008.20
Table S4 : Multi-agent RaspAssistant performance and the single-agent baseline on Study 4.
AgentTypeModelRWPVOther Tools
SupervisorPEVGPT-5.2✗✗✗✗Agent delegation, fitting-loop entry
SetupPEVGPT-5.2✓✓✗✗RASPA manual
ExampleReActGPT-5 mini✓✗✗✗RASPA examples
FileReActGPT-5 mini✓✓✓✗ 
AnalysisPEVGPT-5.4✓✓✗✓Output file parsing
PythonReActGPT-5.2✓✓✓✗Output file parsing
Table S5 : Agent architectures, configured model families, and capabilities. Parentheses indicate case-study configurations where they differ from workflow reproduction.
DimensionDefinitionWeight
Workflow correctnessCompletion of the expected workflow steps in the appropriate order and using appropriate methodological choices.40%
Simulation validityPhysical and computational validity of the simulations, including parameter selection and convergence.40%
Analysis consistencyInternal support and calibration of the scientific interpretation, including uncertainty and model limitations.20%
Table S6 : Workflow-reproduction evaluation dimensions and weights.
DimensionDefinitionWeight
Parameter correctnessCorrectness and completeness of the extracted parameters relative to the reference parameter set.60%
RASPA readinessFraction of generated force-field files that execute in RASPA without correction.40%
Table S7 : Force-field extraction evaluation dimensions and weights.
IDFull-credit requirementPoints
V1Correct structures, species, temperatures, pressures, and compositions for the requested result families.6
V2Supplied force fields and charge convention are used effectively. Required specialized interactions are retained. Effective electrostatics are confirmed from output.7
V3Appropriate supercell replication and cutoff settings are used for the benchmark.6
V4Equilibration and production are credible, and convergence, uncertainty, or an equivalent stability check is demonstrated.6
V5Pressure, loading, heat, geometry, and normalization conventions are reconciled and comparisons are restricted to overlapping domains.7
V6Inputs, completed outputs, warnings, derived values, and report claims are traceable.4
Table S8 : Simulation-validity criteria used for every workflow-reproduction benchmark.
IDFull-credit requirementPoints
I1Species, equations, signs, and reported values are internally correct.5
I2Claims follow the run’s usable outputs. A conclusion of “inconclusive” is accepted when supported.5
I3Small denominators, force-field sensitivity, conflicting models, and sampling limitations are recognized.5
I4Experimental comparison, pure fits, IAST, direct mixtures, breakthrough, and site evidence are weighted according to their reliability. Mechanistic claims have direct support.5
Table S9 : Analysis-consistency criteria used for every workflow-reproduction benchmark.
IDExpected workflow stepPoints
TAM-W1Inspect the structure, charges, experimental metadata, and distinct adsorption and column void fractions.3
TAM-W2Run pure CO 2 and N 2 GCMC at 298, 323, and 353 K over the experimental pressure range.6
TAM-W3Compare unit-matched pure simulations with experiment over the overlapping domains.5
TAM-W4Calculate selectivity and TSN over all four feeds, three temperatures, and the pressure range.7
TAM-W5Use IAST and representative direct mixture GCMC to assess mixture-model reliability.4
TAM-W6Compare breakthrough with the supplied pure-CO 2 /He and CO 2 /N 2 /He experiments.6
Table S10 : Workflow criteria for TAMOF-1 CO 2 /N 2 separation 38 .
Figure S1 : TAMOF-1 diagnostic from Study 1, multi-agent Run 3, comparing IAST and direct-mixture GCMC selectivities for the benchmark based on Ref. 38 . Deviations from the parity line motivate treating IAST-derived selectivities and downstream breakthrough predictions as qualified rather than requiring numerical agreement.
IDExpected workflow stepPoints
ACE-W1Inventory the four structures, material-specific force fields, and experimental states.3
ACE-W2Validate pure C 2 H 2 , CO 2 , and CH 4 isotherms at their native experimental temperatures.6
ACE-W3Validate adsorption heats using compatible loading bases and overlapping domains.4
ACE-W4Validate Fe-MOF-74 CO 2 and C 2 H 2 binding geometries at 298 K.3
ACE-W5Perform the 318 K pure-component study with host–guest and guest–guest evidence.6
ACE-W6Run equimolar mixture GCMC for both gas pairs at 298 K over the pressure range.8
Table S11 : Workflow criteria for C 2 H 2 /CO 2 and C 2 H 2 /CH 4 separation 39 .
Figure S2 : Pure-component validation overview from Study 2, multi-agent Run 2, for the four MOF materials and supplied experimental reference data 39 . Material-dependent disagreement is not itself a scoring failure.
IDExpected workflow stepPoints
M74-W1Audit all six materials and the experimental units and definitions.3
M74-W2Validate CO 2 at 298 K and H 2 at 77 K for all six metals.6
M74-W3Validate CO 2 and H 2 adsorption heats using the correct loading axes.4
M74-W4Validate CO 2 and H 2 binding geometries at 298 K.4
M74-W5Generate and audit 298 K pure CO 2 and H 2 data and fits for process calculations.4
M74-W6Compare IAST with representative direct mixture GCMC and judge reliability.5
Table S12 : Workflow criteria for metal-center effects in M-MOF-74 40 .
Figure S3 : CO 2 isotherms at 298 K from Study 3, multi-agent Run 2, for the six M-MOF-74 materials. Black lines denote simulations and colored circles the experimental reference data 40 . Loadings are in mol kg -1 . The comparison illustrates both successful reproduction of broad adsorption trends and material-dependent deviations. Numerical agreement is not itself a scoring criterion.
IDExpected workflow stepPoints
ZEO-W1Audit structures, cation and restart data, force fields, experimental states, units, and pressure coverage.3
ZEO-W2Calculate the C 3 –C 6 Rosenbluth prerequisites at 298 K and the C 6 values across the isobar temperatures.4
ZEO-W3Simulate and compare propane and propene isotherms for LTA5A and NaY at 298 K.5
ZEO-W4Simulate and compare hexane and 1-hexene isobars for LTA5A and NaY at the experimental pressures.5
ZEO-W5Run equimolar direct-mixture GCMC for all eight frameworks and four chain lengths at 298 K over the pressure range, including 100 kPa.9
ZEO-W6Calculate and audit selectivity versus pressure and at 100 kPa, including denominator-sensitive points.5
Table S13 : Atomic workflow criteria for the olefin/paraffin zeolite benchmark.
CaseSource
EPM2 CO 2Harris and Yung 51
CO 2 in zeolitesGarcia-Sanchez et al. 44
CO 2 in zeolitesFang et al. 52
CO 2 , N 2 , O 2 , and Ar in zeolitesVujic et al. 53
TraPPE-zeoBai et al. 54
Hydrocarbons and permanent gases in zeolitesFindley and Sholl 55
Table S14 : Scope of the force-field extraction benchmark.
Figure S4 : Post-fitting energetic assessment for C 2 H 2 in Fe-MOF-74 at 318 K. The experimental curve is from Bloch et al. 58 . The literature-force-field points were digitized from Ref. 39 . Experimental heats were unavailable to the fitting agent. RaspAssistant results use the final fitted force field. The zero-loading Widom prediction was monitored without an experimental heat reference or use in selection. Error bars show the reported simulation uncertainties and are smaller than the symbols where not visible.
More in this topic

Scientific Workflow Automation

Scientific workflow automation uses software, AI agents, and laboratory systems to plan, execute, validate, and reproduce research tasks.

See all 161 papers

Explore similar work

CardsList
Mar 31, 2026

SimMOF: AI agent for Automated MOF Simulations

Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready structures. Here, we introduce SimMOF, a large language model based multi agent framework that automates end-to-end MOF simulation workflows from natural language queries. SimMOF translates user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results with analysis aligned to the user query. Through representative case studies, we show that SimMOF enables adaptive and cognitively autonomous workflows that reflect the iterative and decision driven behavior of human researchers and as such provides a scalable foundation for data driven MOF research.

Jaewoong Lee, Taeun Bae, Jihan Kim

Department of chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea

Scientific Workflow AutomationMaterials ScienceComputational Materials ScienceMulti-Agent LLM Systems
AskPDF
Mar 30, 2026

Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that invoke available tools and scientific software libraries, and scores executions with an LLM-based judge whose feedback drives workflow refinement. On ScienceAgentBench, Mimosa achieves a success rate of 43.1% with DeepSeek-V3.2, surpassing both single-agent baselines and static multi-agent configurations. Our results further reveal that models respond heterogeneously to multi-agent decomposition and iterative learning, indicating that the benefits of workflow evolution depend on the capabilities of the underlying execution model. Beyond these benchmarks, Mimosa modular architecture and tool-agnostic design make it readily extensible, and its fully logged execution traces and archived workflows support auditability by preserving every analytical step for inspection and potential replication. Combined with domain-expert guidance, the framework has the potential to automate a broad range of computationally accessible scientific tasks across disciplines. Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.

Martin Legrand, Tao Jiang, Matthieu Feraud +5

Université Côte d’Azur, CNRS, ICN, Nice, France · Interdisciplinary Institute for Artificial Intelligence (3iA) Côte d’Azur, Sophia-Antipolis, France · Inria, Université Côte d’Azur, CNRS, I3S, France

Autonomous Research AgentsMulti-Agent SystemsLLM Agent Workflow OptimizationMulti-Agent Orchestration
AskPDF
Dec 22, 2025

VASP Agent: An Agentic Framework for Autonomous First-principles Calculations

Large Language Models (LLMs) are increasingly embedded in agentic frameworks for scientific discovery. First-principles materials computation imposes a demanding standard for autonomy: successful execution depends on internally consistent inputs, supervision of long-running calculations, and verified outputs. Here we present VASP Agent, a coding-agent-centered system that combines reusable domain skills, deterministic tools, workspace-state inspection, runtime evidence, and scientific guardrails to execute multi-step VASP calculations. The system is evaluated across multiple tasks including structural relaxation, bandgap calculation, equilibrium lattice constant determination, and CO/Pt(111) adsorption. VASP Agent completes all evaluated cases, and its computed numerical results are compared with those obtained using pymatgen and other agentic tools. When large deviations occur, the calculation parameters produced by VASP Agent are more appropriate than those produced by LLM-based workflows. Failure analysis shows that errors that terminate fixed pipelines can be diagnosed and recovered under agentic control.

Zeyu Xia, Jinzhe Ma, Congjie Zheng +11

Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China. · Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China. · School of Physical Science and Technology, ShanghaiTech University, Shanghai, 201210, China. +6

AI Coding AgentsComputational Materials Science
AskPDF