Active Inference with People: a general approach to real-time adaptive experiments

2026-03-30

AI Summary

This study addresses the challenges of high computational complexity and methodological fragmentation in real-time adaptive experimentation, which hinder unified support for diverse tasks such as ability assessment, treatment allocation, and active learning. The authors propose a general framework that, for the first time, integrates Active Inference with the online behavioral experimentation platform PsyNet to establish a cross-modal, cross-task adaptive paradigm. This framework supports multiple stimulus types—including textual, visual, and auditory inputs—and enables real-time scheduling and dynamic optimization of large-scale experiments. Empirical results demonstrate that the approach reduces the number of trials by 30–40% in ability assessment and achieves three times higher accuracy than fixed designs in identifying optimal interventions for treatment allocation, substantially enhancing both experimental efficiency and precision.

Abstract

Adaptive experiments automatically optimize their design throughout the data collection process, which can bring substantial benefits compared to conventional experimental settings. Potential applications include, among others: computerized adaptive testing (for selecting informative tasks in ability measurements), adaptive treatment assignment (when searching experimental conditions maximizing certain outcomes), and active learning (for choosing optimal training data for machine learning algorithms). However, implementing these techniques in real time poses substantial computational and technical challenges. Additionally, despite their conceptual similarity, the above scenarios are often treated as separate problems with distinct solutions. In this paper, we introduce a practical and unified approach to real-time adaptive experiments that can encompass all of the above scenarios, regardless of the modality of the task (including textual, visual, and audio inputs). Our strategy combines active inference, a Bayesian framework inspired by cognitive neuroscience, with PsyNet, a platform for large-scale online behavioral experiments. While active inference provides a compact, flexible, and principled mathematical framework for adaptive experiments generally, PsyNet is a highly modular Python package that supports social and behavioral experiments with stimuli and responses in arbitrary domains. We illustrate this approach through two concrete examples: (1) an adaptive testing experiment estimating participants' ability by selecting optimal challenges, effectively reducing the amount of trials required by 30--40\%; and (2) an adaptive treatment assignment strategy that identifies the optimal treatment up to three times as accurately as a fixed design in our example. We provide detailed instructions to facilitate the adoption of these techniques.

Problem

• adaptive experiments
• real-time optimization
• active inference
• unified framework
• computational challenges

Innovation

• Active Inference
• Adaptive Experiments
• PsyNet
• Bayesian Optimization
• Real-time Experimentation