Le Bars, S. | Search bioRxiv

bioRxiv2026

Automation Disrupts, Explanations Restore: The Neural Signatures of Agency Loss and Recovery in Human-AI Interaction

Automation has been shown to weaken the sense of agency (SoA), the experience of controlling ones actions and their outcomes, by disrupting the predictive link between intention and effect. Explainable AI (XAI) has been proposed as a solution, yet the neurocognitive mechanisms through which explanations restore agency remain unclear. Across three EEG experiments using an autonomous-driving paradigm, we examined how automation and different forms of AI explanations modulate explicit agency judgments and early neural markers of agency-related predictive processing. In Experiment 1, automation reduced explicit feelings of control and was associated with reduced sensory attenuation, as reflected by increased P1-N1 amplitudes, decreased N1-P2 amplitudes, and delayed N1 latencies. In Experiment 2, distal (goal-level) explanations partially restored agency and selectively modulated early auditory responses, decreasing P1-N1 and increasing N1-P2 amplitudes. In Experiment 3, combining distal and proximal (trajectory-level) explanations produced the strongest behavioural and neural restoration of agency, yielding a graded attenuation of P1-N1 and enhanced N1-P2 responses along with accelerated N1 latencies. Across all experiments, mismatch negativity (MMN) remained unaffected, indicating that pre-attentive deviance detection is preserved regardless of agency or explainability. Together, these results identify component-specific EEG markers that track fluctuations in the sense of agency and demonstrate that multi-level intention sharing by AI systems enhances both predictive engagement and explicit control experience. This work provides a neurocognitive foundation for designing explainable autonomous systems capable of maintaining user agency.

neuroscience↗

bioRxiv2026

Decoding Agency-Related Neural States During Human-AI Interaction in Autonomous Driving Using EEG and Deep Learning

The sense of agency, the experience of controlling ones actions and their consequences, is a fundamental component of human interaction with autonomous systems. As artificial intelligence increasingly mediates decision-making in domains such as autonomous driving, understanding and monitoring agency-related processes becomes critical for maintaining user engagement, trust, and appropriate levels of control. However, existing approaches to measuring agency rely primarily on subjective reports or event-based neural markers, which are poorly suited for naturalistic and continuous human-AI interaction. In this study, we investigate whether agency-related neural states can be decoded from ongoing electroencephalographic (EEG) activity using deep learning. Across two experiments, we manipulated agency through (i) decision authority (human vs AI control) and (ii) system explainability (AI with vs without intention-based explanations). Behavioral results confirmed that both manipulations significantly modulated participants perceived control. At the neural level, we trained EEGNet-based models to decode agency-modulating experimental conditions from pre-feedback EEG activity. Decoding performance was robust at the intra-subject level and remained significantly above chance across participants using a leave-one-subject-out framework, demonstrating partial cross-subject generalization of agency-related neural representations. Spectral ablation analyses revealed that low-frequency activity, particularly in the delta and theta bands, made the dominant contribution to decoding performance. Complementary time-frequency analyses showed that these bands exhibited increased power under reduced-agency conditions, specifically during the post-keypress, pre-feedback interval. Together, these findings indicate that agency-related information is embedded in continuous, low-frequency neural dynamics associated with predictive monitoring processes. By demonstrating that such information can be decoded from single-trial EEG in an offline setting, this work provides a foundation for future real-time, non-intrusive monitoring of user states in human-AI interaction. These results open new avenues for the development of neuroadaptive systems capable of dynamically regulating automation and explainability to preserve human agency.

bioengineering↗