Simulation-based Optimization for Augmented Reading

2026-02-26

AI Summary

Existing augmented reading systems often rely on heuristic rules, black-box models, or frequent human intervention, making it difficult to systematically optimize text presentation for improved comprehension and task performance. This work proposes modeling augmented reading as a simulation-based optimization problem grounded in resource-rationality theory. We develop a computational framework that simulates how readers process text under cognitive constraints such as attention, memory, and time. By combining offline design-space exploration with online, interaction-data-driven personalization algorithms, our approach enables adaptive interface generation. This method uniquely integrates resource-rational cognitive modeling with simulation-based optimization, facilitating the design of augmented reading systems that are efficient, interpretable, and scalable, while substantially reducing reliance on large-scale human experiments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• augmented reading
• simulation-based optimization
• resource-rational models
• text user interfaces
• cognitive resources

Innovation

• simulation-based optimization
• resource-rational modeling
• augmented reading
• cognitive simulation
• adaptive user interfaces