On this page

Inquiry-based learning (IBL) — a learner-centered pedagogy in which students develop understanding by posing questions, exploring independently, and constructing knowledge through a cycle of inquiry, reflection, and revision, with the instructor scaffolding rather than lecturing. In the AI era, IBL's question-driven, exploration-centered structure has become a focal point: generative AI and LLM tools can serve as interactive "co-inquirers" that support questioning and investigation — but only when designed to preserve rather than bypass the cognitive work of inquiry.

Questions to Consider

  • Inquiry-based learning centers on student-driven questions and the inquiry process itself. How is learning driven by your own question different from learning driven by someone else's?
  • The question is whether AI serves as a 'co-inquirer' supporting your investigation or as a substitute that bypasses the cognitive work. When you use AI to explore a question, who is doing the inquiring?
  • Evidence on AI-supported inquiry is mixed: it improved creative performance and attitudes but not critical problem-solving in one study, and deepened conceptual understanding without boosting AI literacy in another. What does that suggest about what AI alone can and cannot develop?
  • If treating AI output as authoritative risks over-reliance and superficial conclusions, how would you teach students to evaluate AI-generated answers as part of the inquiry cycle?
  • Inquiry connects to productive failure: learners explore before instruction, so struggle itself prepares learning. How might AI that withholds answers and elicits multiple attempts support that struggle rather than remove it?
  • What is the facilitator's role when AI lowers the friction of asking questions? If students can get answers instantly, what does the instructor now need to scaffold that they didn't before?

Introduction

Inquiry-based learning centers on student-driven questions and the inquiry process itself, typically moving through phases (orientation → conceptualization → investigation → discussion → conclusion). It is the broader family under which problem-based learning and project-based learning are often nested: IBL emphasizes the questioning and discovery process, PBL the ill-structured problem, and project-based learning the tangible artifact.

How inquiry-based learning appears in the research

AI as co-inquirer. A systematic review of ChatGPT for inquiry-based learning in STEAM (Jiang et al. (2026), 24 studies) found ChatGPT used mainly in the conceptualization, investigation, and discussion phases — as learning tool, tutor, learning peer, domain expert, and teaching assistant. That use improved performance, critical thinking, engagement, and motivation, while posing risks of over-reliance, hallucination, and superficial conclusions when output is treated as authoritative.

Problem posing as the starting point. A quasi-experiment with 97 third-graders (Dai et al., 2026) showed GenAI chatbots significantly outperformed search engines for science problem posing, improving question quality and producing more integrated epistemic networks while lowering cognitive load.

Cognitive-level patterns in LLM-driven IBL. An exploratory study of 117 interview transcripts and interaction records (Luo et al.) identified 14 interaction patterns across Bloom's cognitive levels, showing how students' prior knowledge shapes LLM use and highlighting the need for scaffolding that targets higher-order thinking stages and mitigates over-reliance.

Outcomes evidence is mixed. An AI-supported IBL experiment in mathematics (Mujib et al.) improved creative mathematical performance and attitudes but not critical problem-solving skills — suggesting AI-IBL mainly supports creativity and affective development. A meta-analysis of 29 experiments (Zhao et al.) found GenAI has a moderate positive effect on higher-order thinking, strongest for problem-solving and with 8–16 week interventions and higher self-regulated learning learners benefiting most. A quasi-experiment with 48 pre-service science teachers in Türkiye (Aydın) using an 8-week AI-supported guided inquiry program (integrating problem- and design-based learning) found significant group-by-time gains in conceptual understanding of photosynthesis and cellular respiration, but no significant effect on AI literacy or self-perceived computational thinking — evidence that AI-IBL can deepen domain understanding while the development of AI/CT competencies requires more explicit, targeted design.

Gousopoulos (2026) isolated the AI contribution from the inquiry itself in a three-group climate study: AI-assisted inquiry outgained inquiry-only peers on decision-making (d = 0.69), with the largest gains in monitoring and adaptive management (d = 1.37), while basic data collection improved equally across all conditions.

Equity and context. A conceptual framework bridges generative-AI co-design with open educational practices to support inquiry-led STEM teaching in under-resourced contexts, using AI-generated, multilingual, contextually relevant simulations.

AI-scaffolded evidence comparison. An and colleagues (2026) show how an AI-powered information-extraction system shifts the undergraduate literature review from summarization toward evidence organization and comparison — students moving from isolated reading to cross-study comparison and evidence-based justification in support of research-based learning and thesis completion. This concretizes how AI can scaffold inquiry processes in STEM undergraduate research.

Why inquiry-based learning matters for AI integration

IBL's question-driven, process-focused structure is the natural home for productive AI use: students learn with AI as a partner rather than from it as a substitute. The evidence converges on a core tension: AI can lower the friction of information retrieval and question formulation (reducing cognitive load and enabling deeper reflection), but without design scaffolding it risks over-reliance and bypassing higher-order cognition. The facilitator's role, the design of scaffolds, and the explicit teaching of evaluation skills are the levers determining whether AI deepens or displaces inquiry.

One study substitutes the facilitator rather than adding a tool beside them. In a four-week pharmacology course, 136 second-year medical students were split between facilitator-led and AI-led problem-based learning. Both arms gained significantly on pre/post multiple-choice tests and the between-group difference was not significant (p = 0.474), but facilitator-led groups scored higher on critical thinking (14.75 against 13.09, p < 0.001) and on the group assessment rubric (26.51 against 24.74, p = 0.035) (Shetty and Rao, 2026). Inquiry outcomes split by kind: content knowledge survived the substitution and the reasoning process did not, which is what it means to say the facilitator is the lever.

Productive failure and inquiry

Productive failure (PF) is the most structured cousin of inquiry-based learning: learners explore problems and generate solutions before direct instruction, then consolidate. Both share the premise that learner-generated attempts (even failed ones) activate prior knowledge and prepare learners to learn from instruction. The AI-era PF research sharpens how AI should scaffold inquiry without short-circuiting it: Kim et al. (2026) derive AI design principles for preserving struggle through problem exploration and solution generation; Puech et al. (2025) show LLM tutors can be steered to withhold answers and elicit multiple attempts; clue-before-correction tasks exemplify clue-based (vs. direct) scaffolding that keeps learners doing the reasoning. These connect inquiry and PF to the broader imperative that AI must not remove the productive struggle through which durable learning forms.

In outdoor field settings the same imperative becomes spatial: GenAI can pre-structure what learners notice before they encounter the evidence, so a field-first sequence that withholds generated explanation until observations and initial interpretations are recorded protects the inquiry (Choi, 2026).

A 66-study map places generative AI beside investigation and least often at orientation. Yahya et al. (2026) coded GenAI use onto the five inquiry phases and found support reported most often in investigation (45 studies, 68.2%), then conclusion (29, 43.9%), discussion (28, 42.4%) and conceptualization (27, 40.9%), with orientation last (20, 30.3%). Eleven studies covered all five phases, 19 covered one and nine named none. Only 8 studies (12.1%) measured inquiry skills, and 4 of those had a comparison condition, so this is a map of where tools were placed rather than what inquiry gained.

Common Misconceptions

"AI is a natural fit for inquiry-based learning because both are exploratory." The fit depends entirely on design: generative AI and LLM tools can serve as interactive co-inquirers that support questioning and investigation only when designed to preserve the student's ownership of the question. Used otherwise, an exploratory student is following an answer rather than conducting an inquiry, and the two look similar from the outside.

"Any AI added to an inquiry unit improves it." The AI contribution has to be isolated from the inquiry itself. Gousopoulos (2026) did this with a three-group design in a climate study: AI-assisted inquiry outgained inquiry-only peers on decision-making (d = 0.69), with the evidence located in a specific outcome rather than in the general superiority of the approach.

"Inquiry is unstructured by definition." The instructor scaffolds, and the structure is in the question design and the reflection cycle rather than in the delivery of content. Removing the scaffold does not make the inquiry more authentic; it makes it unscaffolded.

"Student-led questions will be well-formed if students are interested." Generating a tractable question is the skill being developed, which is why a system that supplies good questions has performed the inquiry skill the activity exists to teach.

Connected Concepts

Connected Articles

Embed this page

Copy the code below to embed this page in a learning management system or other website. The embedded version shows only the page content — it hides the site header, navigation, and footer.