Research questionHow can LLMs augment calibrated energy-adoption ABMs while preserving interpretability, reproducibility, and behavioural validity?Replacing an adoption mechanism with unconstrained LLM reasoning can make behavioural assumptions difficult to interpret and reproduce while risking implausible adoption dynamics. The challenge is to represent behavioural variation and future conditions without losing calibration or behavioural validity. Latest papersRecent research connected to this question, newest first.LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption ModelsEvidence is limited to a calibrated agent-based model of solar PV adoption by Irish dairy farms using bounded conservative, balanced, and optimistic behavioural rubrics plus fixed, rule-validated scenario specifications. Experiments cover multiple policy settings, Monte Carlo worlds, and random seeds; reported outcomes were stable, economically plausible, bounded, and monotonic across behavioural regimes, with up to approximately 13% higher behavioural adoption than the corresponding logistic case.research paper · Sep 4, 2026