Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
Abstract
The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach for efficiently navigating such spaces, but most workflows rely on fixed exploration-exploitation policies that lack the capacity to adapt to shifting constraints in dynamic campaigns typical of self-driving laboratories. In this work, we develop a multi-objective BO framework for alloy design under resource constraints, benchmarking strategies for adaptive policy tuning at each iteration. Our evaluation covers a septenary refractory high-entropy alloy (RHEA) system focused on maximizing melting temperature and minimizing density, and an Fe-Co-Ni-based soft magnetic alloy system targeting saturation magnetization, coercivity, and hardness. We compare an exploitation-focused strategy, a fixed mixed exploratory/exploitative policy, and two distinct LLM-based adaptive strategies with different approaches to batch allocation and campaign signal interpretation, evaluated across baseline and mid-campaign resource event conditions including budget reductions, timeline cuts, and combined disruptions. Our results show that mixed allocation strategies accumulate substantially more mutual information than the exploitation-focused baseline at a proportionally smaller cost to hypervolume and optimization speed, with adaptive strategies outperforming a fixed-mixed allocation policy by adjusting their allocation in response to both evolving campaign statistics and resource constraints. These findings suggest that adaptive resource allocation offers a favorable tradeoff for materials discovery campaigns in reducing predictive uncertainty on Pareto-optimal compositions.
Related
- Divergent strategies and convergent outcomes in autonomous materials discovery
- From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
- Physics-Informed and Knowledge-Driven Generative AI for Autonomous Discovery of Porous Oxide Energy Materials: Opportunities and Challenges
- Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
- From Autonomous Knowledge Generation to Generalizable Property Prediction: A Precision-First Pipeline for Electro-Optic Materials Discovery
BibTeX
@misc{robinson2026agentic,
title = {{Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery}},
author = {Robert Robinson and Shakti Prasad Padhy and Sushant Sinha and Sk Md Ahnaf Akif Alvi and Juan Florez Coronel and Brent Vela and Trevor Hastings and Douglas Allaire and Raymundo Arróyave},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04134},
eprint = {2610.04134},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04134},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
AU - Robert Robinson
AU - Shakti Prasad Padhy
AU - Sushant Sinha
AU - Sk Md Ahnaf Akif Alvi
AU - Juan Florez Coronel
AU - Brent Vela
AU - Trevor Hastings
AU - Douglas Allaire
AU - Raymundo Arróyave
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2610.04134
UR - https://arxiv.org/abs/2610.04134
AB - The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach for efficiently navigating such spaces, but most workflows rely on fixed exploration-exploitation policies that lack the capacity to adapt to shifting constraints in dynamic campaigns typical of self-driving laboratories. In this work, we develop a multi-objective BO framework for alloy design under resource constraints, benchmarking strategies for adaptive policy tuning at each iteration. Our evaluation covers a septenary refractory high-entropy alloy (RHEA) system focused on maximizing melting temperature and minimizing density, and an Fe-Co-Ni-based soft magnetic alloy system targeting saturation magnetization, coercivity, and hardness. We compare an exploitation-focused strategy, a fixed mixed exploratory/exploitative policy, and two distinct LLM-based adaptive strategies with different approaches to batch allocation and campaign signal interpretation, evaluated across baseline and mid-campaign resource event conditions including budget reductions, timeline cuts, and combined disruptions. Our results show that mixed allocation strategies accumulate substantially more mutual information than the exploitation-focused baseline at a proportionally smaller cost to hypervolume and optimization speed, with adaptive strategies outperforming a fixed-mixed allocation policy by adjusting their allocation in response to both evolving campaign statistics and resource constraints. These findings suggest that adaptive resource allocation offers a favorable tradeoff for materials discovery campaigns in reducing predictive uncertainty on Pareto-optimal compositions.
ER -