Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
Abstract
AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can support practical engineering decisions. We present MARS, a hierarchical Multi-Agent Reasoning System for knowledge-grounded material substitution under scientific and manufacturing constraints. We apply MARS to replace per- and polyfluoroalkyl substances (PFAS), a demanding materials-design problem in which substitutes must satisfy functional performance, environmental, experimental, and processing requirements. MARS decomposes substitution into a closed-loop workflow comprising requirement analysis, grounded candidate generation, and manufacturability assessment with process design. The system integrates retrieval-augmented generation, knowledge-graph reasoning, a database of lab-available materials, persistent memory of intermediate results, and rejection-aware iterative feedback. In a PFAS-substitution case study, MARS generates structured material requirements, identifies an evidence-grounded substitute candidate, and develops a lab-scale manufacturing route. In a multi-seed ablation evaluation, MARS achieves the highest overall performance across all three subsystems, with gains that persist when the backbone model is held fixed. These results suggest that hierarchical decomposition, knowledge grounding, and manufacturability-aware refinement improve material-substitution reasoning beyond model capability alone.
Related
- Scaling LLM Agents for Materials Design through Hierarchical Collective Reasoning
- Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge
- Manufacturing-conditioned hierarchical generation of cathode active-material microstructures with global electrode context
- Biomimetic apatite coatings—Carbonate substitution and preferred growth orientation
- Synergistic effect of Mn substitution and ball milling on NaCu 0.2 Fe 0.8− x Mn x O 2 cathode materials for sodium-ion batteries
BibTeX
@misc{hage2026hierarchical,
title = {{Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution}},
author = {Tarjei Paule Hage and Subhadeep Pal and Wei Lu and Yu-Chuan Hsu and Gayla Lyon and Jiezhu Jin and Markus J. Buehler},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14123},
eprint = {2610.14123},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14123},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
AU - Tarjei Paule Hage
AU - Subhadeep Pal
AU - Wei Lu
AU - Yu-Chuan Hsu
AU - Gayla Lyon
AU - Jiezhu Jin
AU - Markus J. Buehler
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.14123
UR - https://arxiv.org/abs/2610.14123
AB - AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can support practical engineering decisions. We present MARS, a hierarchical Multi-Agent Reasoning System for knowledge-grounded material substitution under scientific and manufacturing constraints. We apply MARS to replace per- and polyfluoroalkyl substances (PFAS), a demanding materials-design problem in which substitutes must satisfy functional performance, environmental, experimental, and processing requirements. MARS decomposes substitution into a closed-loop workflow comprising requirement analysis, grounded candidate generation, and manufacturability assessment with process design. The system integrates retrieval-augmented generation, knowledge-graph reasoning, a database of lab-available materials, persistent memory of intermediate results, and rejection-aware iterative feedback. In a PFAS-substitution case study, MARS generates structured material requirements, identifies an evidence-grounded substitute candidate, and develops a lab-scale manufacturing route. In a multi-seed ablation evaluation, MARS achieves the highest overall performance across all three subsystems, with gains that persist when the backbone model is held fixed. These results suggest that hierarchical decomposition, knowledge grounding, and manufacturability-aware refinement improve material-substitution reasoning beyond model capability alone.
ER -