Concept
ICAP Framework
The ICAP Framework (Interactive–Constructive–Active–Passive) — a taxonomy of cognitive engagement developed by Michelene Chi that classifies learner behavior into four modes of knowledge change, ordered from least to most cognitively engaged: passive, active, constructive, and interactive. In AI in education, ICAP provides both a design target (build tools that elicit constructive and interactive engagement rather than passive consumption) and an evaluation lens (measure whether learners and AI systems are actually engaged at the higher modes).(Hingle et al., 2025)(Do et al., 2026)
Questions to Consider
- Think of the last time you 'learned' something by watching a video or reading. The ICAP framework would call that passive. What do you actually retain from passive exposure versus from explaining it to someone else?
- ICAP orders engagement from passive to active to constructive to interactive. Where do AI tools you've used tend to keep learners — and does clicking through adaptive practice count as real engagement or just activity?
- The most consequential shift is from Active to Constructive: generating explanations or new artifacts rather than just applying knowledge. Why might producing something new be the step that actually changes understanding?
- One study found human experts far outperform AI models at labeling engagement levels. If automated systems systematically underestimate engagement, how should we treat 'engagement' metrics generated by AI?
- ICAP shows that a tool that answers for you keeps you passive, while one that prompts and questions pushes you toward constructive and interactive engagement. Which design choice would you make for your learners?
- The framework is used both as a design target and an evaluation lens. How could you use ICAP in your own teaching or design to tell whether learners are genuinely engaged rather than merely active?
Introduction
ICAP is grounded in the assumption that what learners do determines how much and what they learn. Chi's framework posits that as engagement moves from passive to active to constructive to interactive, the nature of knowledge change deepens — from storing, to attending, to integrating new knowledge with prior knowledge, to co-creating knowledge through dialogue. This makes ICAP a powerful analytic tool for AI in education, where the central design question is whether AI assistance supports or displaces learners' cognitive engagement.
The four modes
| Mode | Learner behavior | Nature of knowledge change |
|---|---|---|
| Interactive | Dialogue with another learner or agent, co-constructing meaning; e.g. defending a position, collaborative problem-solving | Co-creating new knowledge through joint, reciprocal activity |
| Constructive | Generating new output beyond the given; e.g. self-explaining, comparing, reflecting, drawing | Integrating new information with prior knowledge to produce novel understanding |
| Active | Manipulating or acting on the material; e.g. taking notes, underlining, pausing to think | Attending to and storing information, sometimes without deep integration |
| Passive | Receiving information without overt action; e.g. listening to a lecture, reading | Storing information, with limited further processing |
ICAP in AI in education
A design target for AI tools
ICAP reframes the central design question for AI in education: an AI tool that answers for the learner keeps them in passive/active modes, while a tool that prompts, questions, and scaffolds can push learners toward constructive and interactive engagement. This aligns ICAP with constructivism pedagogy and with active learning research.(Varga-Atkins et al., 2026)(Hingle et al., 2025)
An evaluation lens for AI agents
ICAP also serves as a measurement framework. In one study, researchers extended ICAP to a 7-point scale to characterize cognitive engagement in collaborative dialogue, then compared trained human annotators with LLM-based labeling (in-context learning, zero-shot prompting, and reflective agents). Human interrater reliability (kappa = 0.906–0.998) far exceeded LLM annotation (kappa = 0.541–0.609), highlighting ICAP's role — and current limits — in automated engagement measurement for learning analytics pipelines.(Do et al., 2026)
Guiding collaborative-dialogue facilitation
Because interactive engagement is the highest ICAP mode, the framework helps locate the value of AI facilitation in online collaborative discussion. Research on LLM facilitation timing shows that when an AI intervenes in a discussion shapes whether it supports or interrupts interactive knowledge co-construction — an ICAP-informed caution that autonomous moderation agents need calibration toward human-like restraint rather than over-eager facilitation.
ICAP and learning analytics design
ICAP underlies critiques of shallow "engagement" metrics: interacting with a dashboard by clicking filters is active, not interactive, engagement. Effective learning-analytics designs elicit self-assessment and two-way dialogue rather than merely displaying data — an implication drawn directly from Chi's framework.(Graf et al., 2026)
The Active→Constructive transition as the pivotal step
Although ICAP describes a hierarchy, the most consequential shift for learning is the jump from Active to Constructive modes (Chi & Boucher, 2023). Active engagement (applying knowledge to similar-but-non-identical scenarios) prepares learners, but it is Constructive engagement — generating explanations, summaries, or new artifacts — that equips them to create new knowledge. This is the crux for AI in education: a tool that keeps learners in the Active mode (e.g., clicking through adaptive practice) may look productive but never pushes them into the constructive generation that yields durable understanding. Collaborative and literacy-focused interventions that deliberately scaffold the Active→Constructive leap tend to show the strongest gains.(Hingle et al., 2025)
The "strongest gains" part of that claim is an inference from the framework rather than a comparison the review ran. The nine-study review behind it (2015–2023) counts how many interventions included each mode (9 passive, 5 active, 7 constructive, 8 interactive), reports no effect size by mode, and notes that no included study relied on a single mode, so nothing in it isolates the Active→Constructive leap (Hingle et al., 2025). The ordering is Chi's; what the review adds is that practitioners combine modes rather than choose one.
ICAP as an adaptive-scaffolding signal in ITS
ICAP's modes can be operationalized as target states that an adaptive tutor selects among to scaffold cognitive engagement based on an evolving student model. In a logic ITS, Dey Tithi et al. dynamically chose between an Active "Guided" worked-example mode and a Constructive "Buggy" example mode. Comparing Bayesian Knowledge Tracing (BKT) against Deep Reinforcement Learning (DRL) and a non-adaptive baseline over 113 students, both adaptive policies improved posttest performance — but in a differentiated way: BKT gave the largest gains to low-prior-knowledge students (helping them catch up), while DRL produced the highest posttest scores among high-prior-knowledge students. This is a concrete demonstration that effectively personalizing the ICAP mode of an intelligent tutor depends on modeling the learner's current knowledge — and that no single mode or adaptive method suits every learner. It connects the ICAP hierarchy directly to adaptive learning and knowledge tracing design.
ICAP as a model of cognitive state for generating human-like agents
Beyond selecting task modes, ICAP has been embedded directly into the cognitive model of a generative educational agent. CogEvolution builds an ICAP-based "cognitive depth perceptron" that maps inputs to a probability distribution across the four ICAP levels, fusing this with evolutionary-inspired state updates and item response theory memory retrieval to simulate a student's cognitive evolution (including transitions such as confusion → insight). Ablations show that removing the ICAP perception module collapses the agent's ability to distinguish shallow from deep learning — evidence that the ICAP taxonomy can serve as a fine-grained, internal measure of cognitive engagement for student simulation, not merely an external evaluation lens.
ICAP anchors assessment of reflective GenAI interaction
ICAP's emphasis on generative, process-level engagement has been adopted by assessment frameworks that evaluate how students learn with generative AI. The DRIVE framework explicitly aligns its core construct — deep reflective interaction with GenAI output — with the kind of generative engagement ICAP identifies as leading to deeper learning, and uses it to distinguish surface consumption from effortful, reflective reworking of AI-generated content. This positions ICAP as a theoretical anchor for designing and measuring meaningful GenAI learning interactions rather than merely tracking usage.
Implications for design and research
- Design for the higher modes. AI tools should prompt learners to generate, explain, and dialogue — constructive and interactive activity — rather than deliver passive content or act as answer machines.(Varga-Atkins et al., 2026)
- Engage learners across modes. Effective AI literacy instruction engages learners at multiple ICAP levels — passive exposure, active manipulation, constructive generation, and interactive dialogue — selecting the mode that fits the learning goal.(Hingle et al., 2025)
- Measure engagement honestly. ICAP gives researchers and designers a common vocabulary for distinguishing genuine cognitive engagement from mere activity — a corrective to shallow student engagement.(Do et al., 2026)
- Watch the human–LLM annotation gap. If automated systems are used to code engagement, their systematic shortfall relative to trained humans must be accounted for.(Do et al., 2026)
Task design, not only tool design, sets the ceiling. Across 829 coded threads in 40 university courses, artifacts produced where dialogue was Constructive or Interactive drew modestly higher peer ratings of final quality (Zhuang et al. (2026)).
Common Misconceptions
"ICAP is a taxonomy for labelling activities." It is a design and evaluation lens with an ordering claim: passive, active, constructive and interactive engagement differ in the learning they produce, so "build tools that elicit constructive and interactive engagement rather than passive consumption" is a design target rather than a classification exercise. Labeling a lesson with a mode without changing what students do has not applied the framework.
"Time on task or interaction volume indexes engagement level." Volume counts activity, not mode. Scrolling is active and passive in different senses at once, and a student generating many clicks may still be receiving rather than constructing. The framework's value is precisely that it distinguishes kinds of engagement that activity metrics lump together.
"An AI tutor automatically produces interactive engagement because it converses." Conversation is the medium rather than the mode. A dialogue where the system supplies every substantive contribution is passive for the learner wearing an interactive interface, which is the same confusion the engagement literature documents between behavioral activity and cognitive investment.
"Higher ICAP modes are always better." They cost more, and the ordering is about learning per unit of the relevant processing rather than about what a lesson should always aim for. Foundational fluency can require active repetition before constructive work is possible; the error is settling there, not passing through.
Connected Concepts
Connected Articles
- Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents
- Systematic review of collaborative learning activities for promoting AI literacy
- Interactive learning dashboards: rethinking learning visualisations as engagement tools
- Multimodal Learning with Generative AI
- To facilitate or not to facilitate: Human and LLM facilitator tendencies in online discussions
- Adaptive scaffolding for cognitive engagement in an intelligent tutoring system
- CogEvolution: A human-like generative educational agent to simulate student's cognitive evolution
- Assessing students' DRIVE: A framework to evaluate learning through interactions with generative AI