OECD Digital Education Outlook 2026: Exploring Effective Uses of Generative AI in Education

Introduction

Early AI-powered pedagogical agents in education were often limited to pre-scripted, rule-based tutoring systems, exemplified by platforms like AutoTutor that simulated tutor-learner dialogue through fixed scripts (Graesser et al., 2005). These systems demonstrated that conversation-based learning with AI could mimic one-on-one human tutoring, yet they operated within tightly controlled dialogues and anticipated student responses. With the emergence of large language models (LLMs) such as OpenAI’s GPT-4 in the 2020s, a new generation of generative AI (GenAI) agents has begun to transform this landscape (Alrobai and Cristea, 2025; Zhang et al., 2024). Unlike their scripted predecessors, GenAI agents can produce contextually relevant and linguistically coherent responses on the fly, allowing much deeper and more natural interactions. This chapter explores how LLM-powered pedagogical agents can transition from static virtual characters to adaptive, conversational partners by leveraging GenAI.

A central example of the chapter will be the Socratic Playground (SPL) system (Hu, Xu and Graesser, 2025), which extends prior research on dialogue-based tutoring with generative AI and was developed by one of the co- authors. The SPL is a working prototype Intelligent Tutoring System (ITS) that integrates GPT-4 to deliver open-ended Socratic questioning and personalised feedback in real time (Hu, Xu and Graesser, 2025). This introduction frames two key questions guiding our inquiry: How do human interactions with GenAI agents differ psychologically and pedagogically from earlier scripted AI tutors, and what new affordances do GenAI agents bring to personalised learning? From a psychological perspective, GenAI agents can emulate human-like conversational nuances and even emotional sensitivity, rather than the mechanical turn-taking of older systems (Córdova-Esparza, 2025). Pedagogically, LLM-driven GenAI agents are capable of tailoring their prompts and explanations to each learner’s inputs in ways that static decision-tree tutors could not, enabling a form of adaptive tutoring that was previously aspirational (Alrobai and Cristea, 2025). For illustration, whereas a traditional AI tutor may offer a fixed hint regardless of students’ affections reflected in their input, a GenAI agent may try to identify and predict these emotional states and tailor its responses accordingly (e.g. when signs of frustration are detected, the GenAI agent can adopt a more encouraging tone to support the learner). These new affordances – ranging from possible on-demand personalisation at scale to the ability to engage in open-ended Socratic dialogue – hold promise for more effective and engaging learning experiences.

At the same time, a generative approach raises critical considerations that reaffirm the enduring centrality of pedagogy. Prior research emphasises that technology’s power must be harnessed in service of sound instructional methods, not as a substitute for them (Koehler and Mishra, 2009). In other words, even the most advanced LLM-based tutor will fall short unless guided by established theories of learning and thoughtful educational design. Therefore, our investigation keeps this pedagogy-first perspective at the forefront. We position generative models as catalysts that can deepen an agent’s persona and dialogue capabilities, provided that these models are integrated into robust teaching frameworks. The Socratic Playground prototype exemplifies how pedagogy can remain central – drawing on well-established tutoring approaches to foster critical thinking and learner reflection – while simultaneously integrating the generative capacities of cutting-edge AI within authentic educational contexts. By revisiting the evolution from rule-based systems like AutoTutor to today’s generative Socratic tutors, this introduction sets the stage for a detailed examination of how these new agents function and how they can be used responsibly to improve learning. The chapter draws on recent research that compares legacy intelligent tutors to next-generation LLM-driven systems (e.g. Hu, Xu and Graesser, 2025) and findings from the literature on AI-powered pedagogical agents in the age of generative AI. The ultimate goal is to articulate a vision for generative learning companions that not only move beyond the limitations of traditional AI tutors but also remain grounded in meaningful pedagogy and human empowerment.

Generative AI meets traditional, AI-powered pedagogical agents

Traditional ITS were largely rule-based expert systems that relied on predefined if-then rules and domain knowledge to emulate human tutors. These systems could provide step-by-step problem-solving support and feedback, but their behaviour was entirely scripted in advance (i.e. a pre-scripted avatar). Studies showed that such ITS, when carefully engineered, could approach the effectiveness of human one-on-one tutoring in certain domains (Graesser et al., 2005; Paladines and Ramirez, 2020). However, building these systems was labour-intensive: crafting the expert rules, questions, expected answers and feedback messages required extensive domain expertise. Each new subject domain meant starting a new rule base from scratch. Most importantly, the rigidity of rule-based tutors also meant they struggled with unanticipated student inputs or questions, constraining the practical scalability and the richness of tutoring interactions of such systems.

By contrast, recent advances in generative LLM like OpenAI’s GPT series can generate fluent, contextually appropriate dialogue dynamically, bringing new opportunities to ITS implementation that excels in generalisability and adaptability compared to traditional pre-programmed tutors (Giannakos et al., 2024; Hu, Xu and Graesser, 2025). It is envisioned that generative AI agents can enable a more flexible tutoring experience, capable of addressing unforeseen questions or novel problem scenarios in real time (Kovari, 2025), something earlier rule-based systems often struggled to achieve.

Advances in dialogue and adaptability

This section further unpacks how the paradigm shift from rule-based intelligent tutoring systems to neural network-driven generative agents in education implicates educational practice and research.

Modern LLMs have achieved a level of conversational fluency and understanding that enables digital pedagogical agents to engage learners in open-ended discussions (Giannakos et al., 2024; Yan et al., 2024). GPT-4, for instance, has demonstrated the capacity to produce human-like explanations, ask clarification questions, and scaffold student thinking through multi-turn dialogue (Zhang et al., 2024). Such models leverage vast pre-trained knowledge and contextual reasoning abilities that far surpass the pattern-matching techniques of earlier ITS (Frank et al., 2024). An LLM-based agent can “improvise” follow-up questions or hints based on a student’s last response, rather than selecting from a fixed menu of replies. Research by Hu et al. (2025) introduced the concept of a Socratic Playground as an exemplar next-generation ITS implementation which uses a GPT-4 core precisely to achieve this kind of dynamic adaptability. In pilot implementations, the generative approach led to significant improvements in the fluidity and personalisation of tutoring dialogues, compared to the more scripted interactions of legacy systems (Liu et al., 2024; Zhang et al., 2024). The agent demonstrated sound abilities to interpret nuanced or partially correct answers with high accuracy and generate new prompts or scenarios accordingly to address the learner’s needs. These capabilities underscore how LLMs empower agents to navigate beyond the anticipated paths charted by designers, making the tutoring experience more responsive to individual learners.

In contrast, previous systems often faced issues when a student’s input did not match any pre-programmed expectation; the dialogue could stall or the agent might give a generic response. Generative models mitigate this by generalising from their training data to handle a variety of inputs, even those not foreseen by developers. They also bring knowledge grounding potential – via retrieval-augmented generation (RAG) or further fine-tuning on downstream, task-specific materials, so that an agent can incorporate up-to-date factual information into its tutoring (Modran et al., 2024). Additionally, LLM-based agents can maintain a form of memory over the tutoring session (often retrain as the context of the session), tracking what concepts have been covered and what misconceptions the student has shown. This is done through mechanisms like conversation history or explicit memory modules that older systems lacked. For illustration, an agent can remember that a student struggled with a concept earlier and later revisit it with additional practice or questions, aligning with Vygotsky’s notion of assisting within the learner’s Zone of Proximal Development (Vygotsky, 1978). By establishing and iteratively refining the learners’ profiles, a GenAI agent can adapt the tutoring session accordingly (e.g. by adjusting difficulty), keeping the challenge level appropriate for the learner – a capability much closer to what a skilled human tutor would do than what earlier scripted tutors could manage.

In practice, prompt engineering techniques are oftentimes adopted to guide the LLM’s behaviour toward an educational role. Developers design prompts that instruct the model to behave like a Socratic tutor, sometimes including structured guidelines or even standardised schemas for representing data (JSON schemas) to enforce pedagogical logic. Such prompt-based control, combined with the model’s generative capacity, enables multimodal responsiveness as well – some agents can now produce not only textual explanations but also formulae, code, or even images on demand to aid understanding (Yan et al., 2024). The ability to generate varied representations (e.g. analogies, examples, visualisations) helps address different modalities of learning, which was difficult for text-bound, pre-authored systems. In summary, GenAI has equipped digital pedagogical agents with a toolkit of affordances that include real-time dialogue generation, deep language understanding, context retention, and content creation. These affordances allow agents to personalise instruction and engage learners more flexibly than earlier systems that were constrained by pre-scripted logic. The remainder of this chapter will further examine what these changes mean for the roles agents can play, how their interactions can be designed, and how to ensure that this technological leap is anchored in effective pedagogy.