Digital energy feedback systems often present static, uniform messages that ignore users’ emotional context, reducing long-term effectiveness. We propose an affect-aware, model-free reinforcement learning framework for personalized energy-feedback nudging. The system extends the classical MAPE-K loop with an Affect–Behavior Decoupling Architecture (ABDA) that processes emotional signals (via real-time facial emotion recognition) and behavioral cues in parallel. By learning when, how, and which nudges to deliver based on the user’s detected affective state and past interaction data, the agent autonomously tailors interventions without explicit pre-programmed rules. We implemented this approach in a simulated smart-home dashboard and conducted a controlled laboratory study. Results show that emotionally adaptive feedback led to higher positive affect and sustained engagement compared to a non-adaptive baseline. The adaptive condition also increased exposure to conservation-relevant cues and produced modest gains in self-reported energy awareness. We position household energy conservation as the application context. Demonstrating direct impact on energy consumption requires longitudinal field studies. The paper contributes with i) an ABDA–MAPE-K design for hybrid affective-behavioral adaptation; ii) a model-free reinforcement-learning agent that discovers personalized nudge policies from data; and iii) an empirical evaluation demonstrating the benefits of affect-sensitive adaptation for engagement and conservation-relevant cueing.

User interface (UI) adaptation plays a crucial role in enhancing user experience by dynamically adjusting to individual preferences and situational needs. This study presents a comparative analysis of Model-Based Reinforcement Learning (MBRL) and Model-Free Reinforcement Learning (MFRL) as intelligent controllers of UI adaptations. We build upon an implementation of MFRL for emotion-driven UI adaptation and integrate an MBRL approach using Monte Carlo Tree Search (MCTS) with Upper Confidence Trees (UCT) for decision planning, along with a neural network for simulating user emotion responses. Experiments were conducted in a mobile EvacuationApp designed for emergency training, where participants interacted with adaptive UIs driven by either MBRL or MFRL. Our findings indicate that MBRL excels in scenarios with predictable user behavior, where a model of the interaction can be learned, whereas MFRL is more effective in dynamic, uncertain environments with frequent changes in user behavior. In our user study, MFRL achieved superior overall performance in eliciting the intended emotional responses, notably increasing users’ happiness level over successive adaptation cycles. This work offers a deep understanding of reinforcement learning-based UI adaptation strategies, examining the benefits and limitations of each approach.

Adaptive games increasingly combine player modeling, affect sensing, and runtime control, but evidence for how large language models (LLMs) and Reinforcement Learning (RL) could participate in such loops remains limited. We present an affect-aware game adaptation architecture that combines a warm-started tabular Q-learning controller with bounded LLM-assisted action suggestion inside a MAPE-K loop. The LLM is not allowed to act freely: it can only recommend one action from a fixed, predefined adaptation menu, while reinforcement learning remains responsible for value updates and policy improvement. We implemented the architecture in CubeWars, a top-down shooter instrumented with browser-side facial-expression sensing and four concrete adaptation levers: difficulty, zombie color, background audio, and modal gameplay prompts. We evaluated three within-subject conditions with 46 participants: a static baseline, RL-only adaptation, and LLM-assisted RL adaptation. The strongest objective result is that both adaptive conditions improved absolute progression outcomes relative to the static baseline, whereas RL-only and LLM-assisted RL did not differ significantly on normalized objective throughput measures. The clearest hybrid-specific benefits were experiential: the LLM-assisted condition produced higher engagement, stronger absorption, and greater awareness of adaptation than the RL-only condition. For affect, the hybrid condition showed the highest mean value on an exploratory reward-relevant emotion composite, but the pairwise hybrid-versus-RL-only contrast did not survive Bonferroni correction; we therefore interpret the affective findings primarily through their per-emotion decomposition and event-level analyses. The paper contributes: 1) a pattern for integrating constrained LLM advice into a self-adaptive interactive system without replacing the underlying RL controller; 2) an artifact-grounded implementation of affect-driven runtime game adaptation in a playable game; and 3) an empirical evaluation showing that, in the present evidence, the main added value of the hybrid design lies in perceived responsiveness and player experience.

The engineering of adaptive user interfaces has traditionally relied on either rule-based systems encoding designer intuitions about user needs or machine learning approaches requiring substantial historical data before achieving effective personalization. We present a technical architecture that leverages Large Language Models as behavioral synthesis engines to enable immediate adaptation from sparse, heterogeneous user signals. Our system integrates three distinct behavioral channels, i) explicit micro-feedback on individual interface elements, ii) spatial priority inferred from manual widget reorganization through drag-and-drop interaction, iii) and attentional investment measured through dwell time during hover events, within a structured prompt engineering framework that continuously regenerates dashboard layouts while maintaining explanatory coherence. The architecture addresses the technical challenge of translating low-level interaction patterns into high-level design decisions through a layered prompt construction methodology that separates temporal context determination, behavioral signal extraction, explicit preference enforcement, and user profile synthesis. The approach combines manually specified behavioral interpretations and temporal heuristics with LLM-mediated synthesis, enabling the reconciliation of multiple simultaneous signals that would be difficult to encode through explicit rules alone. We demonstrate the system through an instantiation in the personal health monitoring domain, including an analytical evaluation of adaptation behavior across multiple scenarios and a working implementation managing fourteen distinct health metrics across seven widget visualization modalities. The evaluation compares profile-driven initialization, multi-signal behavioral adaptation, and presents the resulting interfaces through representative post-adaptation screenshots. The analytical evaluation shows that the system preserves explicit user constraints, keeps user-prioritized metrics in prominent positions, expands widgets that receive sustained attention. The technical contribution comprises the multi-modal behavioral aggregation strategy, the structured LLM prompt engineering approach for maintaining design consistency across regeneration cycles, and the explainability generation mechanism that exposes adaptation rationale to end users. Our work provides a reproducible engineering approach for building LLM-powered adaptive interfaces that can be generalized beyond health dashboards to any domain requiring continuous interface personalization from heterogeneous user behavior. A current limitation is that, while the system can infer and act on behavioral signals, it does not yet incorporate mechanisms to independently verify whether adaptations improve user experience without additional feedback signals.

Interactive computer systems’ designers emphasize the importance of considering humans, their emotions, and behaviors as first-class entities. Emotions are integral parts of human nature, and ignoring that can lead the interactive systems to failure, low quality, or discomfort. User interfaces (UIs) are increasingly becoming adaptive to users’ various characteristics, intending to improve users’ satisfaction, performance, and decisions. However, the previous approaches proposed for supervising such adaptations are not effectively adopted in real-life problems. This paper proposes the novel approach to adapting UIs to users’ emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users’ task completion and satisfaction. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in emergency training. By taking contextual input of the users’ basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while arousing target emotions. The research includes literature analysis, surveys, and further adopting an iterative process in implementation and experimentation. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other possible UI adaptation techniques, i.e., rule-based and sequential adaptation.

Designing and adapting user interfaces (UIs) based on context and individuals' dynamic characteristics is essential to improve user experience and performance. Emotions are a significant aspect of users' characteristics since they lead to certain behaviors. Consequently, adopting emotions in UI adaptation is a crucial task for developers. However, it is difficult considering the various characteristics of emotions, particularly their variability and temporal aspects. This paper presents a framework for UI adaptation covering specific dimensions of emotions and their temporal aspects. More specifically, the mechanism permits UI adaptation to i)different types of emotions categorizations (basic emotions, facial action units, and arousal/valence) and ii) timing (duration) based on different emotions consolidation. Examples from a serious game prototype illustrate the proposed adaptation mechanisms.

Emotions are integral to human nature, and their existence, duration, and evolution could lead to specific behaviors. If emotions and behaviors are ignored in the design of socio-technical systems, they will fail or cause discomfort. User interfaces (UIs) are elements of interactive systems able to trigger or moderate emotions. UIs are increasingly designed adaptive to users' various characteristics, intending to improve their satisfaction, performance, and decisions. However, previous adaptation supervising approaches are not effectively adopted in real life since they neglect the dynamic behaviors of humans or systems. This paper proposes Emoticontrol, a quality-driven approach to adapting UIs to users' emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users' enhanced quality of experience (QoE). The approach also considers improving the software quality of service (QoS) by designing software architecture alternatives. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in evacuation training. By taking contextual input of the users' basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while keeping them emotionally controlled. We consider software performance a crucial QoS; thus, we adopt and test architectures that facilitate an acceptable level of performance. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other UI adaptation techniques.

Emotions significantly affect the human interaction process with computers. They constitute a dynamic user’s characteristic that can be crucial for adapting user interfaces (UI) to the user’s context. However, their impact on UI adaptation concepts and techniques is not well understood. This paper proposes a problem space that studies the design dimensions to be considered in UI adaptation to emotions. In particular, this emotion -oriented problem space for UI adaptation, highlights the temporal aspects of emotions. It is obtained from two literature reviews realized to identify the gaps in existing problem spaces and the potentials of including emotional aspects inside them. The proposed problem space can benefit all adaptive systems that aim to improve users’ and system’s performance based on users’ reactions to the system.