Searcharxiv⌕ Search

arXiv · 2610.02699

LearnAdapt Praxis: Controlled AI Assistance and Evidence Traces for Adult Workplace Learning

Abstract

AI can help adults produce plausible workplace artefacts while leaving their independent reasoning difficult to inspect. LearnAdapt Praxis addresses this design problem through a five-stage learning workspace: Frame, Learn, Build, Validate and Transfer. The application stores an initial response, versioned specifications, coaching records, validation observations, a separate transfer response and facilitator feedback. Project-level server controls restrict coaching, access to earlier work and learner export during an active transfer attempt; they do not establish that a learner avoided assistance outside the application. This technical report describes the implemented architecture and evaluates selected workflow, authority, failure-recovery and provenance properties. A reproducible synthetic rehearsal exercised 120 serial project episodes across three fictional workplace contexts and four injected provider conditions. All 3,990 recorded checks met their specified expectations. The resulting records contained 240 specification versions, 1,200 activity events and 60 stored synthetic hints; 60 injected provider failures produced no fabricated hints. Separate authentication regressions exposed and resolved a session-expiry defect, and limited staging and production checks verified account access and live model connectivity. The evidence supports the tested engineering properties of the recorded release. It does not establish learning gains, model-output quality, unaided assessment validity, population usability or production capacity. The contribution is an implemented arrangement for separating assisted work, project-level assistance withdrawal and inspectable evidence, accompanied by executable tests and an explicit account of what remains to be validated with adult learners.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nizam Kadir. 2026-10-02. LearnAdapt Praxis: Controlled AI Assistance and Evidence Traces for Adult Workplace Learning. https://arxiv.org/abs/2610.02699

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

"Lighting The Way For Those Not Here": How Can Technology Researchers Help Resist the Missing and Murdered Indigenous Relatives (MMIR) Crisis?

Indigenous peoples across Turtle Island face disproportionate rates of disappearance and murder, a genocide rooted in settler-colonial violence and systemic erasure. Technology plays a crucial role in the Missing and Murdered Indigenous Relatives (MMIR) crisis: it perpetuates systemic violence and impedes investigations, yet also enables sites of advocacy, healing, and resistance. For example, Native communities utilize AMBER alerts, digital news, sovereign crowdsourced databases, social media groups, and resistance movements to mobilize searches, amplify awareness, and honor missing relatives. Yet little research in HCI has critically examined the role of technology in shaping the MMIR crisis. Thus, we qualitatively analyze 140 webpages to identify sociotechnical barriers that hinder communities' efforts, while highlighting actions that foster healing, safety, and resilience. We grounded our analysis in stories that resist epistemic erasure through relational accountability, critical humility, cultural sensitivity, and refusal. Finally, we provide recommendations for HCI to recognize self-determination and sovereignty of Indigenous technologies, direct action to support families, and honor Indigenous onto-epistemologies that cease epistemic violence.

cs.CY↗

The impacts of artificial intelligence on environmental sustainability and human well-being

Artificial intelligence (AI) is increasingly being described as a transformative general-purpose technology, yet its impacts on environmental sustainability and human well-being remain poorly understood. Here, we conduct a systematic review of 1,291 studies selected from 6,655 records to map how the literature assesses these impacts. We find that current research provides a fragmented and uneven account of AI's consequences for human well-being and the environment. Environmental studies focus narrowly on energy use and CO2 emissions (72%) and rarely consider systemic effects (11%), while well-being studies are predominantly conceptual and overlook subjective well-being, cognitive capabilities, and upstream supply-chain impacts. Strikingly, 82% of environmental studies portray AI's impacts as positive, but this finding is driven by the large number of application-level studies. Well-being analyses show a near-even split (44% positive; 46% negative). However, this split masks differences across well-being dimensions: impacts on income and health are generally expected to be positive, whereas impacts on inequality, social cohesion, and employment are expected to be negative. Based on our findings, we identify important priorities for future research: environmental assessments should consider systemic effects and indicators beyond energy and CO2, while well-being research should prioritise empirical analysis. More fundamentally, research must consider environmental sustainability and human well-being together, recognising that AI's impacts are deeply interconnected. Towards this aim, we extend an existing three-level framework for the climate impacts of AI to include broader environmental impacts and human well-being, providing a unified basis to assess AI impacts and guide its development towards environmental sustainability and human flourishing.

cs.CY↗

A Semi-Automated System for Generating Dialogue-Based TTS Lessons Using Large Language Models: An Exploratory Study of Educational Potential

This study proposes a semi-automated system for generating dialogue-based lessons using Large Language Models (LLMs) and Text-to-Speech (TTS) technology, and exploratorily examines its educational potential via a practical quasi-experiment. The system augments rather than replaces educators through a three-stage human-in-the-loop workflow (LLM-based slide/narration generation, educator review, automated audiovisual integration), and introduces a novel method for generating Expert-Novice dialogue narration based on cognitive apprenticeship theory. In a study of 245 first-year high school students who sequentially experienced three lesson formats (instructor voice, single-speaker TTS, dialogue TTS; content differed across sessions, limiting format/content separation), we conducted within-subject (Friedman test, N<=183) and repeated cross-sectional (Mann-Whitney U, N=229/206) analyses. TTS audio did not substantially degrade the learning experience versus instructor voice, supported by TOST equivalence testing. Dialogue TTS was significantly superior to single TTS in comprehension (p=.006, q=.025) and cognitive engagement (p=.019, q=.048); enjoyment was non-significant after FDR correction (q=.081) but reached significance after controlling for prior knowledge (proportional-odds model, OR=1.65, q=.025), and these advantages were not attributable to prior-knowledge imbalance. Conversely, single TTS was superior in audio naturalness (p<.001, q<.001, r=-.238), revealing a trade-off between dialogue's benefits and higher extraneous cognitive load. Dialogue format was preferred by 66.9% of learners as most enjoyable (p<.001). These results reflect a fixed-order design; replication is needed before generalizing them as effects of lesson format. This study provides a theoretical and empirical basis for the educational acceptability of TTS audio and for TTS lesson-format design.

cs.CY↗