Human-AI Collaborative Autonomous Experimentation With Proxy Modeling for Comparative Observation

2026-03-12

AI Summary

This work addresses the challenge of defining precise scalar objective functions in high-dimensional materials experiments and the tendency of purely data-driven approaches to overlook essential physical insights, both of which hinder the discovery of novel materials. To overcome these limitations, the authors propose a human-in-the-loop Bayesian optimization framework (px-BO) that incorporates real-time expert pairwise comparisons of candidate materials. Preferences are encoded via a Bradley–Terry model into a learnable surrogate objective, while a probabilistic surrogate model reduces annotation burden and enables online correction. Evaluated on PTO simulations and BEPS experimental data, px-BO significantly outperforms conventional data-driven strategies, enhancing both exploration efficiency and expert control over the search process, thereby facilitating the discovery of new physical phenomena.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameters need a rapid strategic search through active learning such as Bayesian optimization (BO). However, such high-dimensional experimental physical descriptors are complex and noisy, from which realization of a low-dimensional mathematical scalar metrics or objective functions can be erroneous. Moreover, in traditional purely data-driven autonomous exploration, such objective functions often ignore the subtle variation and key features of the physical descriptors, thereby can fail to discover unknown phenomenon of the material systems. To address this, here we present a proxy-modelled Bayesian optimization (px-BO) via on-the-fly teaming between human and AI agents. Over the loop of BO, instead of defining a mathematical objective function directly from the experimental data, we introduce a voting system on the fly where the new experimental outcome will be compared with existing experiments, and the human agents will choose the preferred samples. These human-guided comparisons are then transformed into a proxy-based objective function via fitting Bradley-Terry (BT) model. Then, to minimize human interaction, this iteratively trained proxy model also acts as an AI agent for future surrogate human votes. Finally, these surrogate votes are periodically validated by human agents, and the corrections are then learned by the proxy model on-the-fly. We demonstrated the performance of the proposed px-BO framework into simulated and BEPS data generated from PTO sample. We find that our approach provided better control of the domain experts for an improved search over traditional data-driven exploration, thus, signifies the importance of human-AI teaming in an accelerated and meaningful material space exploration.

Problem

• Bayesian optimization
• human-AI collaboration
• proxy modeling
• material exploration
• objective function

Innovation

• human-AI collaboration
• proxy modeling
• Bayesian optimization
• Bradley-Terry model
• autonomous experimentation