Pair agent-based tools with instructor-provided cognitive scaffolding to bridge the gap between efficient retrieval and higher-order cognition¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends that because students in agent-enriched contexts engage in self-regulated verification loops but "often struggle to spontaneously transition from these lower-order interactions to higher-order cognitive processing without external prompts", instructors should offer guiding strategies or cognitive scaffolding. It also recommends integrating agent-based tools into human-GenAI collaborative learning contexts and providing targeted scaffolding to bridge the prompt engineering gap for non-technical majors.

Design Implications¶

Context¶

Requirements¶

• Instructors available to provide guiding strategies or cognitive scaffolding alongside agent access

Constraints¶

• Without external scaffolding or instructor-led prompts, students rely on GenAI for immediate problem resolution rather than critical inquiry

Target Learners¶

• undergraduate STEM students, especially non-technical majors using GenAI tools

Target Learning Goals¶

• higher-order cognitive processing such as analysis, evaluation, and design

Related Strategies¶

• Four design principles for educational AI that empowers epistemic agency rather than passive offloading
• Embed verification cycles and faded prompt scaffolding into GenAI-supported STEAM tasks

Examples¶

-

Key Sources¶

• Li, X., Liu, Z., Jiang, S., Chen, J., & Chen, W. (2026). The impact of an LLM-based educational agent on learning achievement, cognitive dynamics, and student perceptions in computer science education. International Journal of STEM Education. https://doi.org/10.1186/s40594-026-00641-y