This paper identifies and validates eight core UX principles for human-AI agent interaction in the workplace using a multi-method approach.

The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.

This paper identifies principles and criteria for a positive User Experience (UX) with AI agents and evaluates methods for its measurement.

This paper proposes a taxonomy of interaction requirements for human-AI interaction in public sector ICT procurement to ensure ethical compliance and sustainable value realization.

Two student cohorts designed cognitively accessible GenAI interfaces, leading to structural and experiential scaffolding concepts.

The paper introduces DigitalCoach, a dataset of human expert-novice computer use coaching sessions, and evaluates the ability of state-of-the-art models to teach humans how to use computers.

This paper presents MAP, a hierarchical semantic representation and annotation pipeline for comparing interaction traces across tasks, interfaces, and input modalities.

This paper proposes a new framework for modeling interaction in ubiquitous analytics using distributed cognition and channels and substrates.

A framework for measuring human contributions in human-agent joint production is proposed.

The paper proposes Engagement-aware MPC, a method that plans interaction to maintain user engagement while respecting a workload constraint in human-centered robotics settings.

A new framework, CAPED, is introduced to characterize user skills required for chart authoring.

The XAIxArts workshop explores the operationalisation of Explainable AI in the Arts, focusing on diversity, ideation, and resource development.

The authors investigate failure modes in human-agent interaction and how they change with increasing autonomy.

A prototype annotation tool is presented that allows humans to identify important information and LLMs to match it to system outputs, creating a division of labor for reliable AI evaluation.

This paper presents a system that uses an embodied conversational agent to facilitate objective data reflection in dialogue with users about their personal health data.

This study compared LLM-based conversational interfaces and traditional dashboards for industrial decision tasks, finding that while conversational agents reduce interactional effort, dashboards remai…

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

This paper reconsiders the concept of presence in XR environments by theorizing bodyless presence as a condition where another individual is experienced as existing despite attenuated bodily co-presen…