🤖 AI Summary
This study addresses the challenge of enabling AI systems to interpret human decision-making processes in real time—particularly before decisions are finalized. Methodologically, it introduces a novel human–AI interaction paradigm that integrates cognitive science with deep learning, specifically by embedding evidence-accumulation decision models (e.g., the drift-diffusion model, DDM) into the training pipeline of deep neural networks. The approach jointly models multimodal, time-resolved behavioral and neurophysiological data—including eye movements and neural signals—to capture the temporal dynamics of decision evolution. Key contributions include: (1) a transparent, process-aware AI architecture that natively incorporates sequential behavioral data; (2) significant improvements in both accuracy and latency of inferring latent human decision intent; and (3) a theoretically grounded and technically feasible foundation for trustworthy human–AI collaboration, bridging cognitive plausibility with engineering practicality.
📝 Abstract
Over the past decades, cognitive neuroscientists and behavioral economists have recognized the value of describing the process of decision making in detail and modeling the emergence of decisions over time. For example, the time it takes to decide can reveal more about an agent's true hidden preferences than only the decision itself. Similarly, data that track the ongoing decision process such as eye movements or neural recordings contain critical information that can be exploited, even if no decision is made. Here, we argue that artificial intelligence (AI) research would benefit from a stronger focus on insights about how decisions emerge over time and incorporate related process data to improve AI predictions in general and human-AI interactions in particular. First, we introduce a highly established computational framework that assumes decisions to emerge from the noisy accumulation of evidence, and we present related empirical work in psychology, neuroscience, and economics. Next, we discuss to what extent current approaches in multi-agent AI do or do not incorporate process data and models of decision making. Finally, we outline how a more principled inclusion of the evidence-accumulation framework into the training and use of AI can help to improve human-AI interactions in the future.
