NeuroChat: A Neuroadaptive AI Chatbot for Customizing Learning Experiences

TL;DR

The paper tackles the gap in AI tutoring by enabling real time assessment of a learner's cognitive state using EEG data and integrating this with a generative AI tutor. NeuroChat achieves this through a closed loop where an engagement score embedded in each prompt guides GPT-4 turbo to adapt depth, presentation style, and pacing. In a within-subject pilot (n=24 analyzed), NeuroChat increases cognitive and subjective engagement but does not produce immediate improvements in learning test performance, highlighting both feasibility and the gap between engagement and measurable learning gains. The work suggests a promising direction for adaptive learning that leverages neurofeedback, emphasizes the need for longer term and multimodal studies, and points to broader implications for human AI interaction in education.

Abstract

Generative AI is transforming education by enabling personalized, on-demand learning experiences. However, AI tutors lack the ability to assess a learner's cognitive state in real time, limiting their adaptability. Meanwhile, electroencephalography (EEG)-based neuroadaptive systems have successfully enhanced engagement by dynamically adjusting learning content. This paper presents NeuroChat, a proof-of-concept neuroadaptive AI tutor that integrates real-time EEG-based engagement tracking with generative AI. NeuroChat continuously monitors a learner's cognitive engagement and dynamically adjusts content complexity, response style, and pacing using a closed-loop system. We evaluate this approach in a pilot study (n=24), comparing NeuroChat to a standard LLM-based chatbot. Results indicate that NeuroChat enhances cognitive and subjective engagement but does not show an immediate effect on learning outcomes. These findings demonstrate the feasibility of real-time cognitive feedback in LLMs, highlighting new directions for adaptive learning, AI tutoring, and human-AI interaction.

Figures (5)

• Figure 1: Left. The Muse 2 EEG system made by InteraXon Inc. Right. Electrode locations of Muse 2 headband according to 10-20 System. CC Teixeria, Gomes, and Brito-Costa (2023).
• Figure 2: Overview of the NeuroChat system and user flow. The user connects the Muse headband, undergoes calibration, and interacts with the neurofeedback-driven LLM. Engagement scores are computed and inserted into the prompt unnoticed by the user.
• Figure 3: NeuroChat user interface with exposed EEG metrics in the user prompt and experimenter control menu. The connection to the Muse EEG device happens through the Brain Widget in the top right corner. “Mood mode” activates the EEG metric injection into the user’s prompts, and turning off “Debug mode” allows the experimenter to hide these from the user. Chats, raw and filtered EEG data, and computed EEG metrics from the Muse device are stored in the browser’s native IndexedDB and can be exported from the Settings panel.
• Figure 4: Overview of study procedure (not to scale).
• Figure 5: Distribution of engagement score means in the control and experimental conditions by order (right: z-score normalized).