Simulation-based Optimization for Augmented Reading

TL;DR

This paper presents a novel simulation-based optimization framework for augmented reading systems, enabling adaptive and explainable interface design by modeling human cognitive resource allocation.

Contribution

It introduces a resource-rational model of human reading and two optimization pipelines for designing and personalizing augmented reading interfaces.

Findings

Systematic evaluation of text interfaces using simulated readers.

Real-time personalization of reading interfaces based on ongoing data.

Enhanced scalability and explainability in augmented reading design.

Abstract

Augmented reading systems aim to adapt text presentation to improve comprehension and task performance, yet existing approaches rely heavily on heuristics, opaque data-driven models, or repeated human involvement in the design loop. We propose framing augmented reading as a simulation-based optimization problem grounded in resource-rational models of human reading. These models instantiate a simulated reader that allocates limited cognitive resources, such as attention, memory, and time under task demands, enabling systematic evaluation of text user interfaces. We introduce two complementary optimization pipelines: an offline approach that explores design alternatives using simulated readers, and an online approach that personalizes reading interfaces in real time using ongoing interaction data. Together, this perspective enables adaptive, explainable, and scalable augmented reading design without relying solely on human testing.