Knowledge–Learning–Instruction (KLI) framework as an organizing theory for AI instructional design¶

Design · All designs
Evidence · 1 claim (1 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The KLI framework connects knowledge components, learning processes, and instructional principles to support robust learning. The article states that "effective instruction requires careful alignment among three core elements": Knowledge Components as the goals of learning, Learning Processes describing how learning occurs, and Instructional Principles as the methods facilitating those processes. The authors use KLI to guide the reasoning of their multi-agent systems, grounding AI instructional design in an evidence-based instructional theory rather than leaving pedagogy to user prompts.

Design Implications¶

Context¶

Requirements¶

The system must map subject domain, grade level, standard alignment, and learning objectives into knowledge components, then select learning processes and instructional principles before activity generation

Constraints¶

The study was limited to a single pedagogical framework (KLI) and a specific set of MAS architectures

Target Learners¶

K-12 secondary mathematics and science students

Learning Goals¶

Curriculum-aligned STEM learning objectives from authentic lesson plan libraries

Claims¶

Teachers Prefer Mas Cmd Creativity Context Completeness [+M]

Examples¶

-

Key Sources¶

Jiayi Wang, Ruiwei Xiao, Xinying Hou, John Stamper. (2025). Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design. https://arxiv.org/abs/2508.16659

Page metadata

Field	Value
`type`	`design`
`id`	`kli-framework-guiding-multi-agent-instructional-design`
`title`	`Knowledge–Learning–Instruction (KLI) framework as an organizing theory for AI instructional design`
`description`	`The KLI framework connects knowledge components, learning processes, and instructional principles to support robust learning.`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-12`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `jiayi-wang-2025`

Frontmatter is the page's machine-readable record — see the Schema & Guide.