GradAgent: A Knowledge-Guided Multi-Agent System for Structure-Preserving Gradient-Flow Computation with an Application to Multicomponent Vesicle Dynamics
Abstract
High-order differential operators and nonlinear coupling make it challenging to construct conservative and energy-stable schemes for coupled gradient-flow systems. We present GradAgent, a knowledge-guided multi-agent system that coordinates three agents across model analysis, algorithm design and proofs, and numerical implementation and validation. Independent audits strengthen reliability by uncovering mathematical errors and proof gaps, guiding revisions, and maintaining consistency across stages. In Reconstruction Mode, GradAgent reconstructs 20 published studies and organizes audited knowledge in an extensible knowledge graph (KG), GradAgent-KG, linking model structures, discretization strategies and proofs, implementations, and numerical evidence. In Design Mode, the agents assess the applicability of retrieved knowledge and develop new schemes informed by relevant discretization strategies. Applied to the fully coupled multicomponent vesicle phase-field-fluid model, GradAgent yields three first-order and three second-order schemes across three algorithmic families, including four linear, decoupled schemes. Under stated assumptions, all six schemes conserve membrane component mass and vesicle volume and dissipate their respective temporally discrete energies unconditionally. Comparisons with and without GradAgent-KG show that it promotes diversity in structure-preserving scheme design for this target model. Numerical tests confirm second-order spatial accuracy, the expected temporal orders, conservation, and temporally discrete energy dissipation, while three-dimensional shear-flow simulations agree qualitatively with experiments. These results demonstrate GradAgent's ability to combine reusable knowledge, coordinated reasoning, and independent auditing to develop and validate structure-preserving algorithms for complex coupled systems.
Related
- An energy stable and accuracy-preserving finite volume scheme based on the SAV method with application to wall-distance computation
- Generators of stability-preserving semigroups, spectral gaps, and classical ground-state computation
- Memory-Augmented Phase-Field Modeling: Onsager Formulation, Internal-Variable Lifting, and Structure-Preserving Computation
- Application of Machine Learning to the Computation of Parameters in the SUPG Method for Unstructured and Anisotropic Meshes
- Input-to-state stability of chemical reaction networks with application to molecular computation
BibTeX
@misc{guo2026gradagent,
title = {{GradAgent: A Knowledge-Guided Multi-Agent System for Structure-Preserving Gradient-Flow Computation with an Application to Multicomponent Vesicle Dynamics}},
author = {Zhenlin Guo and Jiale Meng and Shuqi Tang and Haiyan Su and Maosheng Jiang and Kaiwen Shi and Meng Zhao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24871},
eprint = {2609.24871},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24871},
}
RIS
TY - UNPB
TI - GradAgent: A Knowledge-Guided Multi-Agent System for Structure-Preserving Gradient-Flow Computation with an Application to Multicomponent Vesicle Dynamics
AU - Zhenlin Guo
AU - Jiale Meng
AU - Shuqi Tang
AU - Haiyan Su
AU - Maosheng Jiang
AU - Kaiwen Shi
AU - Meng Zhao
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.24871
UR - https://arxiv.org/abs/2609.24871
AB - High-order differential operators and nonlinear coupling make it challenging to construct conservative and energy-stable schemes for coupled gradient-flow systems. We present GradAgent, a knowledge-guided multi-agent system that coordinates three agents across model analysis, algorithm design and proofs, and numerical implementation and validation. Independent audits strengthen reliability by uncovering mathematical errors and proof gaps, guiding revisions, and maintaining consistency across stages. In Reconstruction Mode, GradAgent reconstructs 20 published studies and organizes audited knowledge in an extensible knowledge graph (KG), GradAgent-KG, linking model structures, discretization strategies and proofs, implementations, and numerical evidence. In Design Mode, the agents assess the applicability of retrieved knowledge and develop new schemes informed by relevant discretization strategies. Applied to the fully coupled multicomponent vesicle phase-field-fluid model, GradAgent yields three first-order and three second-order schemes across three algorithmic families, including four linear, decoupled schemes. Under stated assumptions, all six schemes conserve membrane component mass and vesicle volume and dissipate their respective temporally discrete energies unconditionally. Comparisons with and without GradAgent-KG show that it promotes diversity in structure-preserving scheme design for this target model. Numerical tests confirm second-order spatial accuracy, the expected temporal orders, conservation, and temporally discrete energy dissipation, while three-dimensional shear-flow simulations agree qualitatively with experiments. These results demonstrate GradAgent's ability to combine reusable knowledge, coordinated reasoning, and independent auditing to develop and validate structure-preserving algorithms for complex coupled systems.
ER -