Research

Large Language Models (LLMs) can now assist across the economic research lifecycle, yet general-purpose LLMs and agent systems give no assurance that their outputs meet the discipline's bar. We present an agentic-workflow methodology that carries a research question through the full lifecycle, from ideation and literature review through modeling, data, implementation, estimation, and reporting, across seven specialized teams under a cross-team orchestrator, with human-in-the-loop review at each stage. The methodology incorporates two commitments. The first, trustworthy execution, is a shared infrastructure that verifies outputs, records the provenance of every step, bounds each agent's authority, addresses agent-specific threats, and serves every LLM locally on open weights. The second, reasoning as an economist, makes disciplinary checks explicit in the workflow: agents state identification strategies for causal claims, check structural models against stylized facts by simulation, and search for counterexamples to theoretical claims. Together they produce a first research prototype in hours, with every step's provenance and verification verdict recorded. A two-tier framework evaluates the workflows across fourteen dimensions, combining execution-log metrics with a dual-judge LLM-as-reviewer ensemble across all seven teams.

Artificial Intelligence (AI) is adopted far faster by individuals than by organisations, yet most diffusion models treat both populations as homogeneous and independent. We develop an extended Bass model with heterogeneous archetypes, bidirectional cross-group spillovers, endogenous barrier decay, and productivity feedback. Base parameters are estimated from survey data on individual and organisational AI adoption across 45 countries (2020–2025); the extended model is calibrated and simulated over ten years. Two findings emerge: cross-group spillover from individual to organisational adoption is the dominant diffusion accelerator in the cross-country evidence, while within-group imitation is undetectable in the current two-year panel; and heterogeneity generates a 5.2-year spread across firm archetypes in time to 50% adoption, capturing most of the 6-year empirical firm-size gap. The calibrated model simulates overall organisational AI adoption reaching 50% by 2029 and 74% by 2033 under the benchmark calibration, translating into sustained productivity growth. Education and training delivers the largest adoption gain per unit of intervention intensity, while direct subsidies most effectively narrow the adoption gap between large and small firms.

We investigate the long-run relationship between economic growth and inequality in the United Kingdom using an endogenous growth model featuring heterogeneous agents. Our model links entrepreneurial incentives to individual wealth, endogenising the impact of wealth distribution on growth. Estimation via Indirect Inference confirms the model's ability to replicate UK data from 1870 to 2016. Our findings reveal a trade-off between wealth equalisation and growth, with welfare analysis showing that optimal policies depend on priorities: higher income transfers benefit lower-income groups but reduce growth, whereas lower transfers yield the opposite effect.

Does the distribution of construction horizons matter for investment stability beyond its mean? We add competition neglect, firms' underestimation of competitors' future starts, to a local quadratic, multi-type extension of the Kydland–Prescott economy. In the baseline calibration, two structures with the same mean horizon lose local stability when firms neglect about 22% and 67% of competitors' responses, through different modes: reallocation across types versus an oscillation of aggregate capital. Among valid simulations with non-negative starts near the signed reallocation boundary, output volatility changes little while investment volatility rises by about 11%. A frozen held-out test favours a dispersed housing delivery kernel at the specified mean but rejects the model's macro predictions; a restricted search finds no improvement over the nested zero-neglect fit, and investment persistence remains unexplained.