Vision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment
Not on the map. Why?
Abstract (arXiv)
Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and recent sensor observations to anticipate which action a user may prefer. Existing systems typically select actions from predicted user preference likelihoods, but these likelihoods alone do not reveal how reliable the prediction is, which evidence supports it, or why ambiguity remains. In this vision paper, we argue that uncertainty estimation can provide this missing information and substantially change appropriate downstream behavior. Using the example of a home assistant, we introduce the questions that uncertainty estimation aims to answer, i.e. how sure is the assistant about the predicted preference likelihood, whether the confidence come from group-level assumptions or individual's data, and whether likelihood ambiguity reflect the user's intrinsic preference variability or insufficient data for the particular situation. We further introduce uncertainty estimation applications in neighboring domains, such as human trajectory prediction, personalized activity recognition, information-collection, and model-based control. Finally, we draw on insights from neighboring domains to envision how future uncertainty-aware proactive assistants may address key challenges in proactive interaction.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 11 Oct 2026.
Builds on
16 of 37 references.
References · 16
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
- 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
- 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 129
- 2022Adaptive Conformal Prediction for Motion Planning among Dynamic Agentscited by 53
- 2024Towards Human-centered Proactive Conversational Agentscited by 49
- 2021Role of Human-AI Interaction in Selective Predictioncited by 35
- 2021Collaborative Uncertainty in Multi-Agent Trajectory Forecastingcited by 18
- 2020Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discoverycited by 7
- 2024A Safe and Data-efficient Model-based Reinforcement Learning System for HVAC Controlcited by 5
- 2021Probabilistic Human Motion Prediction via A Bayesian Neural Networkcited by 3
- 2019Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Modelscited by 2
- 2025Disentangling Uncertainties by Learning Compressed Data Representationcited by 2
4 more
- 2025Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studiescited by 2
- 2025Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoringcited by 2
- 2026PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaborationcited by 2
- 2026Personalized and Robust Proactive Robot Assistance with Uncertainty-Guided LLM Reasoningcited by 1
Built on by
Not cited yet.