Exploring collaborative problem-solving in AI-assisted robotics education

Prompt engineering (PE) involves creating, improving, and deploying prompts to improve large language model (LLM) performance. Despite its increasing importance, many students lack skills in this area. Although frameworks for prompt design and process exist, theory-based instructional tools for improving prompt engineering skills are uncommon for developing collaborative problem-solving (CPS) skills in Robotics Education. This study adopted a PE strategy in AI-assisted robotics education, particularly for develo…

By the Truvace deskOctober 17, 20261 min read1 sourcePeer-reviewedTRV-2026-1726· cite & verify

In brief

Researchers applied a prompt engineering strategy within AI-assisted robotics education to develop collaborative problem-solving skills. They worked with 243 undergraduates grouped by ability and used epistemic network analysis to map how prompt engineering and teamwork skills co-occurred in conversation.

The work matters because many students lack prompt engineering skills and theory-based instructional tools for building them alongside teamwork are uncommon. The abstract reports pattern differences between ability groups but gives no effect sizes or learning outcome measures, so the size of any benefit is unclear.

Main points

The scaffold has four stages: Alignment, Adaptation, Autonomy, and Innovation.
Discourse was coded with four prompt engineering codes: Alignment Specification, Adaptive Refinement, Auditing, and Innovation.
The sample comprised 243 undergraduates at multiple sites, grouped by ability.
Epistemic network analysis compared conversation patterns among the ability groups.

The gain

A four-stage prompt engineering scaffold in AI-assisted robotics courses revealed distinct prompt engineering and collaborative problem-solving discourse patterns across ability groups of undergraduates.

The rundown

The study starts from a gap: although frameworks for prompt design exist, instructional tools grounded in theory that build collaborative problem-solving in robotics education are uncommon.

Its design was non-randomised, multi-site, and criterion-group comparative. Students were categorised by ability rather than randomly assigned.

Epistemic network analysis identified co-occurrences of prompt engineering and collaborative problem-solving skills. The authors report distinct configurations by ability group and conclude that scaffolding has pedagogical value in a synergetic learning environment.