Agentic AI assistants that autonomously perform multi-step tasks raise open questions for user experience: how should such systems communicate progress and reasoning during extended operations, especially in attention-critical contexts such as driving? We investigate feedback timing and verbosity from agentic LLM-based in-car assistants through a controlled, mixed-methods study (N=45) comparing planned steps and intermediate results feedback against silent operation with final-only response. Using a dual-task paradigm with an in-car voice assistant, we found that intermediate feedback significantly improved perceived speed, trust, and user experience while reducing task load - effects that held across varying task complexities and interaction contexts. Interviews further revealed user preferences for an adaptive approach: high initial transparency to establish trust, followed by progressively reducing verbosity as systems prove reliable, with adjustments based on task stakes and situational context. We translate our empirical findings into design implications for feedback timing and verbosity in agentic in-car assistants, balancing transparency and efficiency.

Generative AI (GenAI) systems are inherently non-deterministic, producing varied outputs even for identical inputs. While this variability is central to their appeal, it challenges established HCI evaluation practices that typically assume consistent and predictable system behavior. Designing controlled lab studies under such conditions therefore remains a key methodological challenge. We present a reflective multi-case analysis of four lab-based user studies with GenAI-integrated prototypes, spanning conversational in-car assistant systems and image generation tools for design workflows. Through cross-case reflection and thematic analysis across all study phases, we identify five methodological challenges and propose eighteen practice-oriented recommendations, organized into five guidelines. These challenges represent methodological constructs that are either amplified, redefined, or newly introduced by GenAI’s stochastic nature: (C1) reliance on familiar interaction patterns, (C2) fidelity–control trade-offs, (C3) feedback and trust, (C4) gaps in usability evaluation, and (C5) interpretive ambiguity between interface and system issues. Our guidelines address these challenges through strategies such as reframing onboarding to help participants manage unpredictability, extending evaluation with constructs such as trust and intent alignment, and logging system events, including hallucinations and latency, to support transparent analysis. This work contributes (1) a methodological reflection on how GenAI’s stochastic nature unsettles lab-based HCI evaluation and (2) eighteen recommendations that help researchers design more transparent, robust, and comparable studies of GenAI systems in controlled settings.

Driving is a cognitively demanding activity increasingly shaped by interactions with in-vehicle systems. However, current voice assistants lack contextual understanding and often struggle to interpret ambiguous user intent that requires disambiguation. This research explores how large language model (LLM)-based in-car assistants can interpret and act on user intent in a safe, context-sensitive, and human-like manner. It is guided by two main research questions: (1) how users express intent through multimodal cues such as speech, gaze, and touch to provide contextual grounding for the LLM, and (2) how the assistant should adapt its timing, output modality, and level of proactivity to the driving situation and social context.

In human-human conversations, a shared visual layer allows conversation partners to refer to visual elements through spatial references - such as “on the left” or “the blue pen next to you”. Current voice user interfaces, however, lack the context needed to interpret such references, limiting their naturalness. This capability is particularly valuable for in-car interactions, where combining voice and graphical interfaces offers opportunities for more fluent and effective interaction while driving. In this work, we integrate a multimodal large language model for an in-car infotainment system to enable the interpretation of spatial references. Through a user study (N=21), we collect and analyze user utterances to investigate within the context of automotive navigation tasks. As a result, we created a taxonomy that categorizes diverse strategies participants used to reference on-screen elements. Our findings contribute a framework for understanding spatial referencing behavior in vehicles and inform the design of future multimodal in-car systems.

Neuromorphic hardware implements biological neurons and synapses to execute a spiking neural network (SNN)-based machine learning. We present SpiNeMap, a design methodology to map SNNs to crossbar-based neuromorphic hardware, minimizing spike latency and energy consumption. SpiNeMap operates in two steps: SpiNeCluster and SpiNePlacer. SpiNeCluster is a heuristic-based clustering technique to partition an SNN into clusters of synapses, where intracluster local synapses are mapped within crossbars of the hardware and intercluster global synapses are mapped to the shared interconnect. SpiNeCluster minimizes the number of spikes on global synapses, which reduces spike congestion and improves application performance. SpiNePlacer then finds the best placement of local and global synapses on the hardware using a metaheuristic-based approach to minimize energy consumption and spike latency. We evaluate SpiNeMap using synthetic and realistic SNNs on a state-of-the-art neuromorphic hardware. We show that SpiNeMap reduces average energy consumption by 45% and spike latency by 21%, compared to the best-performing SNN mapping technique.

Spiking Neural Networks (SNNs) are widely deployed to solve complex pattern recognition, function approximation and image classification tasks. With the growing size and complexity of these networks, hardware implementation becomes challenging because scaling up the size of a single array (crossbar) of fully connected neurons is no longer feasible due to strict energy budget. Modern neromorphic hardware integrates small-sized crossbars with time-multiplexed interconnects. Partitioning SNNs becomes essential in order to map them on neuromorphic hardware with the major aim to reduce the global communication latency and energy overhead. To achieve this goal, we propose our instantiation of particle swarm optimization, which partitions SNNs into local synapses (mapped on crossbars) and global synapses (mapped on time-multiplexed interconnects), with the objective of reducing spike communication on the interconnect. This improves latency, power consumption as well as application performance by reducing inter-spike interval distortion and spike disorders. Our framework is implemented in Python, interfacing CARLsim, a GPU-accelerated application-level spiking neural network simulator with an extended version of Noxim, for simulating time-multiplexed interconnects. Experiments are conducted with realistic and synthetic SNN-based applications with different computation models, topologies and spike coding schemes. Using power numbers from in-house neuromorphic chips, we demonstrate significant reductions in energy consumption and spike latency over PACMAN, the widely-used partitioning technique for SNNs on SpiNNaker.