The review, led by Xiaowen Liu and Haoli Zhao of Xi’an University of Technology together with colleagues, analyzed 72 peer-reviewed empirical publications from 2019 to 2025. Following the established JBI and PRISMA-ScR methodological guidance, the team searched four major databases—Web of Science, Scopus, PubMed and IEEE Xplore—and supplemented the results with backward and forward citation searches. Rather than sorting the studies by the specific gadget involved, the authors took a more conceptually ambitious approach: they classified every study into one of four mutually exclusive pathways defined by the dominant interaction mechanism, a framework they argue moves beyond device-based categories to focus on what actually organizes the intervention.

The four pathways are extended reality, or XR, which encompasses virtual and augmented reality systems; socially assistive robotics, or SAR, in which physical robots mediate therapeutic interaction; exergames and embodied-interaction systems, or EXG, which engage the body through movement-based play; and hybrid or adaptive systems, or HYB, which combine multiple modalities or adjust their behavior dynamically. The distribution across these categories is telling. XR dominated the landscape with 25 publications, or 34.7 percent of the total, followed closely by socially assistive robotics with 23 publications, or 31.9 percent. Exergames accounted for 13 publications, or 18.1 percent, while hybrid and adaptive systems made up the remaining 11 publications, or 15.3 percent. The near-parity between XR and SAR suggests that the two most visible faces of assistive technology in autism research—digital worlds on one hand, embodied machines on the other—are developing in parallel rather than one displacing the other.

Just as striking is what these technologies are being asked to do. Social communication appeared as a target outcome in 49 of the 72 publications, a commanding 68.1 percent, and cognition or executive function featured in 32 publications, or 44.4 percent. At the other end of the spectrum, daily-living and safety-related skills appeared in only 5 publications, a mere 6.9 percent, and sensory processing in just 3, or 4.2 percent. The imbalance is significant because sensory processing differences and adaptive daily-living skills are core features of the autism profile with profound real-world consequences. The review’s authors point to this as a clear signal that the technology pipeline, whatever its strengths, is concentrating its firepower on a narrow band of outcomes while leaving other critical domains underexplored.

The technical sophistication on display across the included studies is considerable. In the XR pathway, systems range from fully immersive head-mounted displays used in randomized trials of psychological and behavioral intervention to augmented reality coloring books designed to teach children to focus on specific nonverbal social cues. Some platforms integrate multi-modal sensing to assess children while they train, fusing what the system presents with what it measures. Others embed cognitive behavioral therapy within immersive environments, as in a randomized feasibility trial that paired virtual reality with CBT to treat specific phobias in young people on the spectrum. The underlying logic is consistent: virtual environments allow clinicians to control, repeat and gradually scale social scenarios that would be unpredictable or overwhelming in the real world, providing a rehearsal space where difficulty can be tuned to the individual child.

The socially assistive robotics pathway tells a complementary story. Humanoid platforms such as the NAO robot have been deployed to train imitation skills using human action recognition, to support joint attention in comparative studies against typically developing peers, and even to assist minimally verbal children in communication-focused therapy. Researchers have built long-term personalization into in-home robots, tracked gaze behavior across months of in-home deployment, and run randomized controlled trials comparing robot-assisted pivotal response treatment against the same therapy delivered without robotic support. One recurring theme in this literature is predictability: robots can be engineered to behave with a consistency and simplicity that human interaction partners cannot always maintain, which may lower the social demands placed on autistic children and create a bridge toward human-human interaction. Yet studies have also documented how visual and hearing sensitivities affect robot-based training, a reminder that the sensory profile of each child constrains what any single technology can deliver.

The exergame and embodied-interaction pathway brings the body into the loop. Motion-tracking games and somatosensory systems have been used to train motor skills, executive function and postural balance, with randomized and crossover trials examining effects on inhibitory control and restricted and repetitive behaviors. This pathway reflects a growing recognition that motor, cognitive and socio-cognitive mechanisms are intertwined in autism, and that physical activity delivered through engaging game formats can target several of them simultaneously. Augmented reality game-based cognitive-motor training and virtual reality rehabilitation studies sit at the intersection of this pathway and the XR category, illustrating why the authors chose to classify studies by interaction mechanism rather than by surface technology: the same headset can serve fundamentally different intervention logics depending on how the interaction is structured.

Perhaps the most forward-looking findings concern the hybrid and adaptive systems pathway, and here the numbers reveal how early the field still is. Only 11 publications fell into this category, and just 5 studies—6.9 percent of the total—used physiologically or neurally driven closed-loop adaptation, meaning systems that read signals such as brain activity or heart rate variability and adjust their behavior in real time. These include brain-computer interface video games using neurofeedback to train attention, wearable EEG neurofeedback systems built on machine learning algorithms, and mobile augmented reality neurofeedback training games. Closed-loop adaptation represents the logical endpoint of personalized intervention: a system that senses when a child is dysregulated or disengaged and responds automatically. But at fewer than one in ten studies, it remains a frontier rather than a foundation, and the review’s authors explicitly call for greater transparency about how these adaptive mechanisms work, since an opaque algorithm that changes therapy on the fly is difficult to evaluate, replicate or trust.

The methodological picture that emerges from the review is one of a field in transition. Only 18 of the 72 publications, or 25 percent, used randomized designs, meaning the majority of the evidence base rests on weaker study architectures that are more vulnerable to bias and less able to establish causal effects. The authors also highlight the lack of longitudinal evaluation in real-world settings: many systems are validated in short laboratory sessions with researchers present, leaving open the question of whether gains persist and generalize to homes, classrooms and communities. Their recommendations are correspondingly concrete—strengthen pathway-specific reporting so that studies within each interaction mechanism can be compared, extend evaluation over longer time horizons in authentic environments, and open up the black box of adaptive systems.

What makes this review more than a bookkeeping exercise is the framework itself. By organizing the literature around interaction mechanisms rather than devices, the authors have created a shared vocabulary that connects system design to intervention goals and participant needs. A clinician choosing between a robot partner and a virtual scenario is not merely choosing hardware; they are choosing between fundamentally different interaction logics with different demands on the child. Mapping those logics makes it possible, for the first time, to see where the evidence is dense, where it is thin, and where the next generation of studies should aim. As multimodal technologies continue to migrate from research labs into clinics and homes, that kind of structural clarity may prove to be the field’s most valuable intervention yet.

Subject of Research: Multimodal human–computer interaction interventions for children and adolescents with autism spectrum disorder

Article Title: Multimodal Human–Computer Interaction Interventions for Children and Adolescents With Autism Spectrum Disorder: A Scoping Review

Article References: Liu, X., Zhao, H., Zhang, W., Zhang, C., & Liu, X. (2026). Multimodal Human–Computer Interaction Interventions for Children and Adolescents With Autism Spectrum Disorder: A Scoping Review. Journal of Autism and Developmental Disorders. https://doi.org/10.1007/s10803-026-07555-2

Image Credits: AI Generated

DOI: 10.1007/s10803-026-07555-2

Keywords: autism spectrum disorder, multimodal human-computer interaction, extended reality, socially assistive robotics, exergames, virtual reality, augmented reality, neurofeedback, social communication, scoping review, assistive technology, closed-loop adaptation

The idea is deceptively simple. Professional XR today often inherits the visual language of consumer systems, with saturated color palettes, gamified treatments, glowing ornaments, and stylized cartoon-like characters. An engineer who spends her days in CAD software and precision instrument panels may read such an interface as foreign to her working order, regardless of how capable it is. The researchers call the opposite pole of this spectrum native visual language, a design approach that aligns the interface with the chromatic restraint, grid discipline, typographic register, and stylistic fidelity that a professional community already expects from its artifacts. Crucially, this fit is relational rather than absolute: the same interface could feel native in one organization and jarring in another, because organizational visual conventions differ.

What makes the study pointed is its diagnosis of technology acceptance research. Established models such as TAM2, TAM3, and UTAUT have long recognized that adoption is socially conditioned, capturing this through constructs like subjective norm and social influence, beliefs about what colleagues and superiors expect. But none of these instruments contains a single item addressing how a system looks. In an immersive medium, the authors argue, that omission is consequential: the interface occupies the entire visual field, and the user is represented inside it. Visual dissonance is therefore proposed not as a new social determinant but as an XR-specific interface property that operationalizes an already-recognized social mechanism at the level of visual form, something that can be manipulated, measured, and designed for.

To test the construct empirically, the team ran a within-subject survey with 96 professional workers drawn from heterogeneous sectors. Each participant compared paired stimuli across three XR interface components: workspace layouts, meaning the arrangement of panels in the space surrounding the user; avatar representations, the depiction of the user inside that environment; and data dashboards, three-dimensional visualizations of quantitative datasets. Within each pair, functional content was held constant, with the same panel sets, the same business-casual identity, and the same data structure, so that only the visual register varied. The aligned variants followed professional conventions, while the dissonant variants adopted saturated palettes, playful geometry, and a stylized consumer-VR aesthetic. Participants rated each variant on professionalism, trustworthiness, appropriateness, and design quality, and then made a committed choice about which variant they would trust in their professional work.

The results split in a way the authors did not fully anticipate. On the graded rating scale, only the avatar component produced a statistically reliable credibility difference, with a small-to-medium effect size of d = 0.39. Workspace layouts and dashboards showed numerical advantages for the aligned variants that failed to reach significance. But when participants were forced to commit to one variant, the picture changed dramatically: 86 percent chose the professionally aligned avatar and 78 percent chose the aligned dashboard, both far above chance, while workspace choices remained balanced at roughly 47 percent. The dashboard effect, invisible on the graded measure, emerged only when a decision was required, suggesting that visual dissonance in data-bearing artifacts operates through a decision threshold rather than a continuously graded evaluation.

Even more striking was what the item-level analysis revealed about avatars. The credibility gap was carried by judgments of professionalism, design quality, and appropriateness, but not by trustworthiness, a dissociation consistent with prior research on avatar realism and self-presentation, including the Proteus effect and the enclothed cognition literature. The avatar, the researchers note, is the component in which the interface depicts the professional self in front of colleagues and stakeholders, making identity-incongruent treatments a direct source of dissonance. Yet in a further twist, the avatar was the only component where participants’ explicit awareness items did not exceed the scale midpoint, meaning people may not consciously attribute their reactions to a category labeled visual design at all.

The study also dismantled the assumption that visual sensitivity is a single dispositional trait. The three component-specific credibility gaps were mutually uncorrelated, with pairwise correlations near zero, meaning sensitivity to dissonance in one component predicts nothing about sensitivity in another. Individual differences did matter, but in component-localized ways. The Centrality of Visual Product Aesthetics scale, a validated measure of how much people value design, amplified the credibility gap only in the avatar component. Professional role made no significant difference between knowledge workers and operational workers.

Perhaps the most counterintuitive finding concerns experience. One might expect that workers familiar with XR would habituate to its consumer aesthetics and grow tolerant of gamified interfaces. The opposite occurred. Prior XR familiarity amplified rather than reduced the credibility gap, correlating at r = 0.36 with the avatar gap, and a multiple regression confirmed experience as the stronger predictor, with standardized beta = 0.41 against 0.27 for aesthetic centrality. Familiarity, the authors conclude, does not relax expectations about how a workplace interface should look; it consolidates them. The more time professionals spend in immersive systems, the sharper their implicit criteria become.

The methodological lesson may prove as influential as the substantive one. Graded self-report alone, the study suggests, systematically underestimates visual dissonance precisely where the construct is most tied to professional identity, because participants either cannot articulate the effect or decline to commit it to a Likert scale. Committed-choice comparison, which has long been known in image quality assessment to yield lower measurement variance than single-stimulus rating, exposed effects that the rating instrument missed entirely. The authors call for behavioral protocols, including response latencies, eye tracking, and deployment-context decisions, to triangulate the construct in future work, alongside factorial experiments that manipulate single visual variables independently.

The limitations are acknowledged candidly: the stimuli were static images judged in vignette fashion rather than lived experiences inside a running system, the sample skewed toward knowledge workers aged 25 to 34 with low XR familiarity and came from a single national context, and the six visual variables co-varied within each pair rather than being crossed factorially. Still, the design directions that follow are concrete: stricter avatar alignment with workplace visual norms, an experience-scaled visual register, dashboards evaluated against committed-choice criteria, and a wider tolerance margin for ambient workspace layouts. When asked directly, professionals converged on context-adaptive options, with roughly 60 percent preferring adaptive color palettes, adaptive spatial organization, and adaptive customization scope over fixed alternatives. As XR hardware matures and the Industry 5.0 agenda pushes immersive tools toward the factory floor and the operating theater, the study positions the visual register of professional XR as a measurable adoption factor, one that current acceptance models recognize only indirectly, and one that designers ignore at the cost of credibility.

Subject of Research: The effect of visual design alignment between extended reality interfaces and workplace conventions on perceived professional credibility

Article Title: Extended reality visual language for professional contexts: a study on visual dissonance

Article References: Musolino, F., & Fiorentino, M. (2026). Extended reality visual language for professional contexts: a study on visual dissonance. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-026-05134-y

Image Credits: AI Generated

DOI: 10.1007/s12652-026-05134-y

Keywords: extended reality, visual dissonance, avatars, dashboards, technology acceptance, user interface design, virtual reality, augmented reality, professional credibility, organizational culture, aesthetic sensitivity, native visual language

The review followed a rigorous scoping methodology aligned with the PRISMA Extension for Scoping Reviews and the Joanna Briggs Institute Population–Concept–Context framework. The team searched three engineering and computer science databases, Scopus, the ACM Digital Library and IEEE Xplore, for publications between January 2000 and February 2025. In a striking methodological decision, the researchers deliberately excluded the word rhythm itself, along with synonyms such as timing, tempo, flow and cadence, from their search strings. Because rhythm is conceptually complex and used differently across disciplines, searching for it directly would have flooded the results with irrelevant work. Instead, they captured the broad landscape of augmentation and feedback technologies in sport, then examined whether the holistic, expert-understood concept of rhythm was actually being addressed. After screening 442 unique records from an initial pool of 529, the team distilled the literature down to 129 technology-focused studies.

The first headline finding is the era of the wearable sensor. Wearable devices were the primary technology in 48.8 percent of the included studies, and inertial measurement units, the tiny accelerometer and gyroscope packages that detect motion, appeared in 44.2 percent of the entire corpus. Their dominance reflects maturity, low cost and high ecological validity: unlike laboratory motion capture rigs, IMU-based wearables can record rhythm-relevant features such as step frequency, stance duration and inter-movement intervals directly in the field, on the track, in the pool or on the slopes. Examples in the corpus range from flexible sensor networks for sprint and jump biomechanics to smart dumbbells with embedded inertial units that evaluate strength training form in real time. For anyone hoping to quantify the temporal texture of movement, the sensor hardware problem is, in essence, already solved.

The second headline is a turn toward seeing rather than feeling the data. Computer vision systems accounted for 20.2 percent of primary technologies and extended reality systems for 22.5 percent, together representing more than 40 percent of the corpus. Visual capture technologies spanning ordinary RGB cameras, LiDAR and full motion capture appeared in one third of all hardware implementations. This suggests a field diverging into two camps: one that attaches discrete sensors to the body, and another that leverages optics and immersive environments where users quite literally inhabit their own performance data. The rise of extended reality, in particular, signals a shift beyond passive data logging toward experiential interfaces, exemplified by virtual reality training systems evaluated with national-level sitting volleyball players that produced measurable skill improvement.

Underpinning both camps is artificial intelligence. Explicit use of AI or machine learning to generate or adapt feedback appeared in 42 percent of the included studies. Rather than being the primary technology, machine learning frequently serves as the translation layer that converts raw sensor streams into meaningful, actionable cues. Examples range from wearable systems using deep learning to provide adaptive auditory feedback for weight training to computer vision pipelines that assess landing form in basketball. In principle, this is exactly the kind of computational machinery needed to move from simple real-time alerts toward the sophisticated, personalized, adaptive feedback systems that the authors argue elite sport actually requires.

Yet the feedback side of the equation reveals a striking monoculture. Visual feedback dominated the literature, appearing in 81 percent of studies, most commonly as on-screen graphs and numerical displays delivered via smartphone or tablet in 61 percent of the corpus. A representative system for hammer throw training gives coaches a real-time plot of the wire tension curve, elegant for a coach watching but demanding that an athlete look away from their own movement. The authors point out that visual attention during performance is a limited and critical resource, and studies on augmented reality workout systems have found that on-screen cues can impose additional cognitive load during dynamic movement. For an embodied skill like rhythm, which is often felt as much as seen, defaulting to screens may be actively counterproductive.

The untapped opportunity, the review argues, lies in the senses sport has largely ignored. Auditory feedback appeared in only 25 percent of studies and haptic feedback in a mere 11 percent. Their temporal affordances make them natural candidates for rhythm cueing: the ear is a timing organ, and the skin can feel a pulse without any attention being paid. The few studies that do explore these channels hint at real promise. Interactive sonification, in which movement is converted into continuous sound, has provided effective low-latency feedback on body roll in swimming, and electrical muscle stimulation has been used to directly correct running foot-strike patterns. Crucially, the auditory channel often remains unengaged during high-concentration physical exercise, leaving bandwidth free for guidance that refines rather than disrupts an athlete’s flow.

The review also documents a troubling gap between who builds these systems and who is supposed to benefit from them. Elite and professional athletes were the target population in only 26 percent of studies, and coaches in just 18.5 percent, while novices and amateurs, often university students, are heavily over-represented. The most common application domain was general fitness training, and 70 percent of studies targeted posture or technique form, compared with only 35 percent targeting timing or tempo, 20 percent targeting consistency or flow, and 12 percent targeting stride parameters. In other words, the literature measures discrete kinematic snapshots when rhythm is an integrated temporal quality. Elite performers possess refined, idiosyncratic motor programs; their challenge is micro-adjustment of an already optimized system, requiring higher-resolution feedback than novice learning studies typically provide.

The proof problem compounds the population problem. Although 81 percent of systems were empirically evaluated, the primary goal of most evaluations was system usability or feasibility, in 45 percent of studies, while only 22.5 percent measured performance improvement and 8.5 percent measured skill acquisition. Nearly one in five studies, 19.4 percent, reported no formal evaluation at all. Perhaps most tellingly, only 26.5 percent of studies explicitly measured rhythm or a direct synonym as an outcome variable. Systems for tennis swing classification, for example, celebrated machine learning model accuracy rather than any change in player skill. The result is a literature full of working prototypes with largely unevaluated training impact.

The authors distill these observations into four challenges, concerning what is sensed, who is studied, how feedback is delivered and what proof exists, and offer them as exploratory, hypothesis-generating directions rather than evidence-based prescriptions. Their near-term proposal is compelling in its simplicity: couple the already mature wearable inertial sensing platforms with continuous, low-latency, non-visual feedback such as movement sonification or complementary haptic cues, and design evaluations that separate technical validation, user experience and genuine performance outcomes as distinct levels of evidence, a trajectory they map onto the Technology Readiness Level framework from proof-of-concept to proof-of-impact. The review has limitations, including its restriction to English-language, technology-indexed literature across three engineering databases, so field-level conclusions about rhythm training await a cross-disciplinary synthesis. But the message to sports engineers is clear: the sensors are ready, the audio and touch channels are wide open, and the athletes at the top are still waiting for technology that speaks their temporal language.

Subject of Research: Human augmentation technologies and feedback modalities for training rhythm in elite sport

Article Title: Augmenting rhythm: a scoping review of technologies and feedback modalities in elite sport

Article References: Hossain, M. T., Lindeman, R. W., Ingram, M., & Lukosch, S. (2026). Augmenting rhythm: a scoping review of technologies and feedback modalities in elite sport. Sports Engineering, 29(2), Article 32. https://doi.org/10.1007/s12283-026-00562-7

Image Credits: AI Generated

DOI: 10.1007/s12283-026-00562-7

Keywords: rhythm, elite sport, wearable sensors, inertial measurement units, real-time feedback, sonification, haptic feedback, extended reality, computer vision, artificial intelligence, sports engineering, scoping review

The research, published open access in the Journal of Ambient Intelligence and Humanized Computing, addresses a gap that has grown as extended reality applications increasingly call on conversational agents for real-time guidance. Large language models have transformed what spoken assistants can do, replacing rigid dialogue trees with flexible, open-ended exchange. But in immersive, task-oriented environments, an agent must satisfy demands that go well beyond answering correctly: it must stay grounded in the task and the surrounding scene, respond within the tight timing of natural turn-taking, and offer help without breaking the user’s sense of presence. Menus, panels and controller commands pull attention away from the hands-on work; speech promises a more direct channel, particularly when assistance is needed mid-action rather than before or after it.

Whether an assistant should also read emotion from speech has remained an open question. Human voices carry information far beyond their linguistic content, and acoustic-prosodic features such as pitch, intensity, rhythm and pausing patterns offer partial evidence about a speaker’s affective state. In principle, an agent that detects frustration, hesitation or elevated effort could modulate its tone, phrasing and level of detail to better match the user’s needs. Previous work has examined conversational agents in extended reality, LLM-based dialogue and affect-aware systems largely in isolation or in pairs, but fully integrated evaluations combining spoken dialogue, language-model generation and real-time prosody-based adaptation in task-oriented immersive settings have been rare, and the empirical consequences of such adaptation for both experience and task execution were unclear.

To test the idea, the Salerno team designed a modular client-server system built around three layers. The client, developed in Unity 6 and running on standalone Meta Quest-class headsets, handles rendering, speech acquisition through the Meta Voice SDK, transcription via Wit.ai, gesture-based interaction through Meta’s hand-tracking SDKs, and voice playback through Meta Text-to-Speech. The backend, implemented as Python micro-services, hosts the computationally heavy work: a Dialog Orchestrator that queries GPT-4o-mini using the transcription and the retained dialogue history, and a speech emotion recognition model based on Whisper Large V3 that has been fine-tuned for emotion classification. Communication between the layers relies on JSON messages and streamed audio, with asynchronous exchanges deliberately chosen to avoid blocking operations and preserve conversational continuity.

The architectural elegance lies in running semantic and affective processing in parallel, so that emotional inference never delays a response. Raw audio is accumulated until roughly twenty-five seconds of speech are available, and the resulting affective estimate, complete with a confidence score, is stored in a short-lived memory valid for up to ninety seconds. When the orchestrator processes a dialogue request, it retrieves the most recent valid estimate if one exists; if not, the reply is generated without affective conditioning at all. Crucially, the emotional descriptor serves only as an additional conditioning signal. It shapes the wording, interpersonal tone, reassurance, response length and explanatory detail of the language model’s output, while leaving the procedural facts, the task objective, the agent’s voice and even its visual behavior untouched, so that affective conditioning is the only difference between the two experimental configurations.

The agent itself appears as a deliberately non-anthropomorphic symbolic sphere anchored in the workspace, whose brightness and surrounding animation signal whether it is idle, listening or speaking. Prior research on embodied agents suggests that less humanlike representations can strike a better balance between recognizability, expressiveness and comfort, especially when the system is not meant to emulate a person. Participants, all university students with little prior exposure to immersive technology and almost no laboratory experience, wore a Meta Quest 3 headset and carried out a nine-step chemistry procedure: placing a flask on a stand, measuring and transferring resorcinol, adding ethanol, heating the mixture, preparing a nitrating mixture from sulfuric and nitric acid, and observing the final color change. The chemistry framing was chosen not to study chemistry education but because such a procedure demands the coordination of physical manipulation, sequential decision making, spatial attention and continuous spoken dialogue that characterizes procedural assistance scenarios generally.

The results revealed a striking trade-off. On the System Usability Scale, the adaptive condition scored an average of 88.6 against 81.4 for the non-adaptive one, a statistically significant difference with a large effect size, and both ratings fall within what standardized guidelines describe as the excellent range. Yet participants guided by the empathetic agent took substantially longer to finish, averaging 693 seconds against 503 seconds, and engaged in more conversational turns, averaging 20.3 against 16.3, both differences statistically significant with large effects. Overall workload, measured with the NASA Task Load Index, showed no significant difference between conditions, though the subscales told a subtler story: the adaptive group reported lower physical and temporal demand but higher frustration, suggesting that the emotional adaptation softened the felt pressure of the task even as it lengthened it, and occasionally irritated users when responses seemed more elaborate than the moment required.

The qualitative interviews added texture to the numbers. Participants in the adaptive group frequently described the agent as more human, friendlier and more attentive, with remarks that the interaction felt natural, like dealing with someone trying to help rather than a device issuing commands, and that the agent’s manner made the procedure less stressful during its most complex phases. Others found the empathy excessive for a short task, noting that the agent sometimes explained too much or offered comfort when none was needed. The non-adaptive group, by contrast, described the interaction as simple, clear and direct, and offered notably fewer spontaneous comments, which the authors suggest may itself reflect lower engagement with an assistant perceived mainly as a functional tool.

The researchers are careful about interpretation. The longer completion times and extra turns cannot, on their own, distinguish productive support from unnecessary verbosity, and the authors argue the pattern is best read as a genuine trade-off between concise execution and a richer conversational experience, one whose desirability depends on context: extra dialogue may be an asset in education and training but a liability in time-critical procedures. They recommend treating affect-aware adaptation as a context-dependent design strategy rather than a default upgrade, triggering it selectively during hesitation, repeated clarification requests or errors, and regulating not just emotional tone but response length and detail. Limitations include the student-only sample, the single procedural domain, and reliance on vocal prosody alone; future work should explore multimodal affect recognition combining gestures, gaze, task progress and physiological signals, while addressing the privacy and transparency questions that such sensing inevitably raises. What the study establishes is that emotional attunement measurably reshapes how people experience machine guidance in immersive environments, making the interaction feel more supportive at the price of speed, and giving designers an evidence-based lever for deciding when that price is worth paying.

Subject of Research: Affect-aware conversational adaptation using LLM-driven dialogue and prosody-based emotion recognition in mixed-reality procedural tasks.

Article Title: Affect-aware conversational adaptation in mixed reality procedural tasks

Article References: Cantone, A. A., Ercolino, M., Sebillo, M., & Vitiello, G. (2026). Affect-aware conversational adaptation in mixed reality procedural tasks. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-026-05125-z

Image Credits: AI Generated

DOI: 10.1007/s12652-026-05125-z

Keywords: mixed reality, conversational agent, large language model, affect-aware adaptation, speech emotion recognition, extended reality, GPT-4o-mini, human-computer interaction, procedural guidance, System Usability Scale, vocal prosody, immersive training