Skip to main content

# Shared Decision Making

2 related articles

Subscribe to updates

arXiv Oct 26, 2026
Assistive agents in shared driving learn to guess intent first, improving torque alignment and collision rate in racing and urban driving
Assistive agents in shared control must act on the human's intent while staying legible enough for the human to respond in real time. Dream2Assist adds intent inference to a recurrent state-space world model and trains the assistive policy through fictitious co-play, anticipating discrete human objectives without overriding human agency. Three human-subjects studies and a preliminary on-vehicle deployment span high-speed racing (N=30) and urban driving with richer intent structure (N=10), where intent conditioning yields measurable improvements in torque alignment and collision rate.
Assistive agents in shared control must act on the human's intent while staying legible enough for the human to respond in real time. Dream2Assist adds intent inference to a recurrent state-space world model and trains the assistive policy through fictitious co-play, anticipating discrete human objectives without overriding human agency. Three human-subjects studies and a preliminary on-vehicle deployment span high-speed racing (N=30) and urban driving with richer intent structure (N=10), where intent conditioning yields measurable improvements in torque alignment and collision rate.
Jonathan DeCastro（First author）
Dream2Assist Model-Based Reinforcement Learning World Model Intent Inference Shared Decision Making
Urogynecology Oct 1, 2026
ChatGPT-generated surgical decision aids for pelvic floor disorders had high patient understandability, but about 30% of topics fell short on accuracy and overall readability was high
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
In this cross-sectional study, six urogynecologists developed six questions comparing two treatment options for common urogynecological conditions and entered them into ChatGPT to create decision aid tools; patients and physicians then rated understandability with a Patient Education Materials Assessment Tool, physicians rated reliability with a modified DISCERN instrument and accuracy on a 5-point Likert scale, and readability was assessed with the Flesch-Kincaid Reading Ease score, showing high patient and physician understandability for all tools, fair reliability with an average mDISCERN score of 26, accuracy below 4 (unfavorable) on 2 of the tools, and a high reading level required overall.
University of California, Irvine
Carolyn S Chen（First author, Corresponding author）
ChatGPT Shared Decision Making

You’re all caught up