You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: content/blog/_index.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,7 +19,7 @@ sections:
19
19
The paper presents a teacher-centred LLM-based multi-agent system that supports teachers in developing personalized educational materials according to students characteristics.
20
20
21
21
<div class="news-button-container">
22
-
<a href="/blog/facet-preprint-2025/" class="news-button">read blog post →</a>
22
+
<a href="/blog/facet-preprint-2025/" class="news-button">read more →</a>
FACET is a teacher-centred LLM-based multi-agent system that supports teachers in developing personalized educational materials according to student characteristics, such as motivation, self-concept and performance.
13
+
14
+
## problem
15
+
16
+
Teachers face increasingly diverse classrooms, yet despite the recognized importance of differentiation, limited time and resources make it difficult to translate personalization into everyday practice.
17
+
18
+
## key features
19
+
20
+
-**Multi-agent architecture**: Incorporates multiple agents that simulate both students and the teacher
21
+
-**Personalization**: Delivers tailored learning materials based on individual students' affective, motivational, and performance-related attributes
22
+
-**Teacher-centred design**: Supports teachers through AI-driven assistance while preserving their pedagogical autonomy and authority
23
+
24
+
## outcome
25
+
26
+
Together with teachers, we are developing a teacher-centered, LLM-based multi-agent system designed to create AI-generated personalized teaching materials. Our approach goes beyond performance optimization by also taking into account students' motivational and affective dimensions, ensuring a more holistic understanding of learning processes.
27
+
28
+
[read more about the FACET framework](https://arxiv.org/abs/2508.11401)
29
+
30
+
[interestedt in co-creating the AI tool? ](mailto:gonnermann-mueller@zib.de)
caption: 'Cognitive load-based Augmented Reality design for vocational training'
8
+
focal_point: 'Center'
9
+
preview_only: false
10
+
---
11
+
12
+
This research project develops human-centred design principles for Augmented Reality (AR) using cognitive theories, such as cognitive load theory.
13
+
14
+
## problem
15
+
16
+
Occupations in crafts and production are characterized by hands-on activities, and the knowledge required for them is difficult to convey through PDFs or traditional classroom instruction. While augmented reality (AR) offers the opportunity to learn directly on the job and through practical examples, many users report experiencing distraction and cognitive overload when using AR systems.
17
+
18
+
## research questions
19
+
20
+
- How does visual guidance affect cognitive load in AR environments?
21
+
- What are the optimal design patterns for reducing cognitive load?
22
+
- How can eye-tracking data inform AR interface design?
23
+
24
+
## key findings
25
+
26
+
- Visual guidance significantly reduces cognitive load in AR learning tasks
27
+
- Specific design patterns facilitate learning with AR
28
+
- Individual differences in cognitive processing affect AR usability
29
+
30
+
## outcome
31
+
32
+
This research contributes to the theoretical understanding of cognitive load in AR environments and provides practical guidelines for designing more effective AR learning systems.
33
+
34
+
## read more
35
+
36
+
[Paper on visual guidance →](https://aisel.aisnet.org/icis2024/)
37
+
38
+
[Paper on AR-specific design guidelines →](https://onlinelibrary.wiley.com/doi/10.1111/jcal.13095)
<p>Teachers face increasingly diverse classrooms, yet despite the recognized importance of differentiation, limited time and resources make it difficult to translate personalization into everyday practice.</p>
25
-
</ul>
26
-
<p>FACET is a teacher-centred LLM-based multi-agent system that supports teachers in developing personalized educational materials according to student characteristics, such as motivation, self-concept and performance.</p>
27
-
<p><strong>key features:</strong></p>
28
-
<ul>
29
-
<li>Multi-agent architecture: Incorporates multiple agents that simulate both students and the teacher</li>
30
-
<li>Personalization: Delivers tailored learning materials based on individual students’ affective, motivational, and performance-related attributes</li>
31
-
<li>Teacher-centred design: Supports teachers through AI-driven assistance while preserving their pedagogical autonomy and authority</li>
32
-
</ul>
33
-
<p><strong>outcome:</strong></p>
34
-
<ul>
35
-
-> Together with teachers, we are developing a teacher-centered, LLM-based multi-agent system designed to create AI-generated personalized teaching materials. Our approach goes beyond performance optimization by also taking into account students’ motivational and affective dimensions, ensuring a more holistic understanding of learning processes.
36
-
</ul>
37
-
<p><a href="https://arxiv.org/abs/2508.11401" target="_blank">read more about the FACET framework →</a></p>
38
-
</div>
39
-
</div>
14
+
title: projects
15
+
design:
16
+
columns: '1'
17
+
css_class: 'text-center'
40
18
41
-
- block: markdown
19
+
- block: collection
42
20
content:
43
-
text: |-
44
-
<div class="project-card">
45
-
<div class="project-image">
46
-
<img src="/images/projects/cognitive-load-study.jpg" alt="Cognitive Load AR Study" />
47
-
</div>
48
-
<div class="project-content">
49
-
<h3 class="project-title">Cognitive load-based Augmented Reality design for vocational training</h3>
50
-
<p class="project-subtitle">AR design</p>
51
-
<p><strong>problem:</strong></p>
52
-
<ul>
53
-
<p>Occupations in crafts and production are characterized by hands-on activities, and the knowledge required for them is difficult to convey through PDFs or traditional classroom instruction. While augmented reality (AR) offers the opportunity to learn directly on the job and through practical examples, many users report experiencing distraction and cognitive overload when using AR systems.</p>
54
-
</ul>
55
-
<p>This research project develops human-centred design principles for Augmented Reality (AR) using cognitive theories, such as cognitive load theory</p>
56
-
<p><strong>research questions:</strong></p>
57
-
<ul>
58
-
<li>How does visual guidance affect cognitive load in AR environments?</li>
59
-
<li>What are the optimal design patterns for reducing cognitive load?</li>
60
-
<li>How can eye-tracking data inform AR interface design?</li>
61
-
</ul>
62
-
<p><strong>key findings:</strong></p>
63
-
<ul>
64
-
<li>Visual guidance significantly reduces cognitive load in AR learning tasks</li>
65
-
<li>Specific design patterns facilitate learning with AR</li>
66
-
<li>Individual differences in cognitive processing affect AR usability</li>
67
-
</ul>
68
-
<p><strong>outcome:</strong></p>
69
-
<ul>
70
-
-> This research contributes to the theoretical understanding of cognitive load in AR environments and provides practical guidelines for designing more effective AR learning systems.
71
-
</ul>
72
-
<p><a href="https://aisel.aisnet.org/icis2024/" target="_blank">Paper on visual guidance →</a> | <a href="https://onlinelibrary.wiley.com/doi/10.1111/jcal.13095" target="_blank">Paper on AR-specific design guidelines →</a></p>
0 commit comments