Agentic education · Learning science

Actionable companion · Motivation & engagement

Learning with agency: Fostering children’s creativity through LLM-driven storytelling with a social robot

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Children · stage unspecified. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Creativity is an important skill that is known to plummet in children when they start school education that limits their freedom of expression and their imagination. On the other hand, research has shown that integrating social robots into educational settings has the potential to maximize children’s learning outcomes. Therefore, our aim in this work was to investigate stimulating children’s creativity through child-robot interactions. We fine-tuned a Large Language Model (LLM) to exhibit creative behavior and non-creative behavior in a robot and conducted two studies with children to evaluate the viability of our methods in fostering children’s creativity skills. We evaluated creativity in terms of four metrics: fluency, flexibility, elaboration, and originality. We first conducted a study as a storytelling interaction between a child and a wizard-ed social robot in one of two conditions: creative versus non-creative with 38 children. We investigated whether interacting with a creative social robot will elicit more creativity from children. However, we did not find a significant effect of the robot’s creativity on children’s creative abilities. Second, in an attempt to increase the possibility for the robot to have an impact on children’s creativity and to increase the fluidity of the interaction, we produced two models that allow a social agent to autonomously engage with a human in a storytelling context in a creative manner and a non-creative manner respectively. Finally, we conducted another study to evaluate our models by deploying them on a social robot and evaluating them with 103 children. Our results show that children who interacted with the creative autonomous robot were more creative than children who interacted with the non-creative autonomous robot in terms of the fluency, the flexibility, and the elaboration aspects of creativity. The results highlight the difference in children’s learning performance when inetracting with a robot operated at different autonomy levels (Wizard of Oz versus autonoumous). Furthermore, they emphasize on the impact of designing adequate robot’s behaviors on children’s corresponding learning gains in child-robot interactions.

What kind of evidence is this?

Embodied learning agents · Evidence synthesis

Stage: Children · stage unspecified. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

The experiment took place at the local Museum of Technology in Stockholm, Sweden, where 38 children participants were recruited, aged 5–10 years old ( Mean=7.84 , SD=1.61 ). Six children who either withdrew from the activity or did not interact with the robot were excluded, leaving data from 32 participants (15 males, 17 females) for analysis.

Limitations and uncertainty · source passage

In our Study 1, we investigated whether a wizard-ed robot portraying verbal creativity in a collaborative storytelling interaction will render children more creative in their story ideas. Despite previous research that suggests that interacting with a creative robot in a different setting of figural, constructional and verbal creativity yields to more creative behavior from children Ali et al. (2019), Ali et al. (2021a), Ali et al. (2020b); in our study, results showed no significant effect of changing the robot’s behavior between creative and non-creative on children’s creativity skills. Thus, H1 was rejected. We attribute the results to the fact that the tele-operator wizarding the robot chose story ideas randomly from a limited creative versus non-creative pool of ideas which led to the children expressing their frustration at the robot’s non-contextual changes to their story lines. Figure 2B displays an example of the robot’s non-contextual addition to a child’s story where the robot uses the crocodile to generate a new story idea without building on the child’s previous idea.

Design the system before the pilot

Compare the embodied interaction with an equivalent human-led or screen-based activity. Separate the effects of novelty and social presence from learning. Review physical access, sensory needs and adult supervision.

  • Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Establish the participants’ ages, developmental needs and educational setting from the full paper before selecting an intervention. Use adult-mediated activity and preserve hands-on and peer learning. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Evaluate an age-appropriate independent task after the interaction. Do not infer a preschool or primary-school effect when the paper does not establish that population. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Maha Elgarf; Hanan Salam; Christopher Peters. Fostering children’s creativity through LLM-driven storytelling with a social robot. Frontiers in Robotics and AI (2024-12-13). https://doi.org/10.3389/frobt.2024.1457429

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.