Timing the Message: Language-Based Notifications for Time-Critical Assistive Settings

2025-09-09

AI Summary

In time-critical driver assistance scenarios, existing language-based assistance systems neglect end-to-end latency across linguistic communication, human comprehension, and physical action execution, thus failing to jointly optimize timeliness and informativeness. This paper formulates notification timing as an Enhanced-State Markov Decision Process (ES-MDP), the first framework to explicitly co-optimize latency across language generation, cognitive interpretation, and motor response stages. By integrating reinforcement learning with extended state-space modeling, we develop a pipeline to generate synthetic offline classification datasets that emulate realistic human response delays. Experiments on synthetic human trials demonstrate that our approach improves task success rate by over 40% compared to latency-agnostic baselines, achieving unprecedented synergy between temporal responsiveness and semantic richness—thereby transcending the conventional paradigm focused solely on content generation.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Generation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

In time-critical settings such as assistive driving, assistants often rely on alerts or haptic signals to prompt rapid human attention, but these cues usually leave humans to interpret situations and decide responses independently, introducing potential delays or ambiguity in meaning. Language-based assistive systems can instead provide instructions backed by context, offering more informative guidance. However, current approaches (e.g., social assistive robots) largely prioritize content generation while overlooking critical timing factors such as verbal conveyance duration, human comprehension delays, and subsequent follow-through duration. These timing considerations are crucial in time-critical settings, where even minor delays can substantially affect outcomes. We aim to study this inherent trade-off between timeliness and informativeness by framing the challenge as a sequential decision-making problem using an augmented-state Markov Decision Process. We design a framework combining reinforcement learning and a generated offline taxonomy dataset, where we balance the trade-off while enabling a scalable taxonomy dataset generation pipeline. Empirical evaluation with synthetic humans shows our framework improves success rates by over 40% compared to methods that ignore time delays, while effectively balancing timeliness and informativeness. It also exposes an often-overlooked trade-off between these two factors, opening new directions for optimizing communication in time-critical human-AI assistance.

Problem

• Optimizing timing for language-based notifications in assistive settings
• Balancing timeliness and informativeness in critical communication
• Addressing delays in verbal conveyance and human comprehension

Innovation

• Augmented-state Markov Decision Process for timing
• Reinforcement learning with offline taxonomy dataset
• Balancing timeliness and informativeness in notifications