% ============================================================================
% UQO Working Paper Template — Economics / Finance
% ============================================================================
\documentclass[12pt,letterpaper]{article}

% --- Encoding & Language ---
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage[english]{babel}

% --- Page Layout ---
\usepackage[
  letterpaper,
  top=1in,
  bottom=1in,
  left=1in,
  right=1in
]{geometry}

% --- Typography ---
\usepackage{mathptmx}          % Times-like font (text + math)
\usepackage{microtype}         % Improved typographic refinements
\usepackage{setspace}
\onehalfspacing                % 1.5 line spacing

% --- Math ---
\usepackage{amsmath,amssymb,amsthm}
\newtheorem{proposition}{Proposition}
\newtheorem{lemma}{Lemma}
\newtheorem{corollary}{Corollary}
\theoremstyle{definition}
\newtheorem{assumption}{Assumption}
\newtheorem{definition}{Definition}
\theoremstyle{remark}
\newtheorem{remark}{Remark}
\usepackage{longtable}
\usepackage{array}
\usepackage{pdflscape}

% --- Tables ---
\usepackage{booktabs}
\usepackage{tabularx}
\usepackage{multirow}
\usepackage{threeparttable}
\usepackage{siunitx}
\sisetup{
  input-symbols = {()},
  table-format  = -1.3,
  parse-numbers = false
}

% --- Figures ---
\usepackage{graphicx}
\usepackage{subcaption}
\usepackage{float}

% --- Colors & Links ---
\usepackage[dvipsnames]{xcolor}
\usepackage[
  colorlinks  = true,
  linkcolor   = NavyBlue,
  citecolor   = NavyBlue,
  urlcolor    = NavyBlue,
  breaklinks  = true
]{hyperref}
\hypersetup{pdftitle={Can Autonomous AI Agents Discover the Fundamental Value of Real Estate? Evidence from Quebec Transactions and Multi-Agent Deliberation}, pdfauthor={Simon-Pierre Boucher}}

% --- Bibliography ---
\usepackage[authoryear,round,semicolon]{natbib}
\bibliographystyle{aer}

% --- Captions ---
\usepackage[
  font       = small,
  labelfont  = bf,
  labelsep   = period,
  justification = justified,
  singlelinecheck = false
]{caption}

% --- Headers & Footers ---
\usepackage{fancyhdr}
\pagestyle{fancy}
\fancyhf{}
\renewcommand{\headrulewidth}{0pt}
\fancyfoot[C]{\thepage}

% --- Section Formatting ---
\usepackage{titlesec}
\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}
\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}
\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}

% --- Appendix Support ---
\usepackage[toc,page]{appendix}

% --- Misc ---
\usepackage{enumitem}
\setlist{nosep,leftmargin=*}

% ============================================================================
% METADATA — Edit these fields for each working paper
% ============================================================================
\newcommand{\WPnumber}{26}
\newcommand{\WPtitle}{Can Autonomous AI Agents Discover the Fundamental Value of Real Estate?}
\newcommand{\WPsubtitle}{Evidence from Quebec Transactions and Multi-Agent Deliberation}
\newcommand{\WPdate}{October 2026}
\newcommand{\WPversion}{1.0}
\newcommand{\WPabstract}{%
  Committees of role-specialised language-model agents that debate before they answer are increasingly proposed as valuation tools. We ask whether the debate adds information. In a preregistered experiment on 631,866 arm's-length residential sales registered in Quebec between 2021 and 2026, evaluated under a leakage-audited as-of information set, we compare a hedonic regression, a hierarchical repeat-sales model, gradient boosting and a conformal automated valuation model with a single language model, twelve independent role-specialised agents, structured debate of one to four rounds, debate with a blinded skeptic and deterministic verification, a placebo committee and a cost-matched single agent, all on identical evidence packets. A model of valuation as decentralised information aggregation shows that opinion exchange contracts dispersion without reducing error, that evidence exchange helps only outside the common view, and that no linear deliberation beats the best round-0 pool. The data agree: on the test subsample the debate reaches a mean absolute log error of 0.158 against 0.159 for the silent committee, 0.157 for the placebo and 0.163 for the cost-matched agent; every preregistered paired contrast includes zero, and rounds halve the agents' disagreement without moving accuracy. Committees match the automated valuation model (0.171 on the full test partition) but state intervals thirty percent too narrow, and in the 2026 holdout every agentic arm overvalues by ten log points where the AVM is unbiased. A two-round debate costs about 1.5 US dollars per property. Forecasting accuracy is kept distinct from fundamental value, which is triangulated with 92,089 resales, rents and user cost.
}
\newcommand{\WPkeywords}{automated valuation models, large language models, multi-agent deliberation, information aggregation, house prices, calibration, appraisal, Quebec}
\newcommand{\WPjel}{R31, C53, C45, D83, G21}

% --- Author ---
\newcommand{\WPauthor}{Simon-Pierre Boucher}
\newcommand{\WPaffiliation}{%
  Département des sciences administratives\\
  Université du Québec en Outaouais%
}
\newcommand{\WPemail}{simon-pierre.boucher@uqo.ca}
\newcommand{\WPaddress}{%
  Gatineau -- Pavillon Alexandre-Taché\\
  283, boulevard Alexandre-Taché\\
  Gatineau, Québec, Canada J9A 1L8%
}

% ============================================================================
% DOCUMENT
% ============================================================================
\begin{document}

% --- Title Page ---
\input{sections/titlepage}

% --- Main Body ---
\input{sections/introduction}
\input{sections/literature}
\input{sections/theory}
\input{sections/setting}
\input{sections/data}
\input{sections/architecture}
\input{sections/design}
\input{sections/results}
\input{sections/ablations}
\input{sections/calibration}
\input{sections/fundamental}
\input{sections/welfare}
\input{sections/limitations}
\input{sections/conclusion}

% --- References ---
\newpage
\bibliography{references}

% --- Appendix ---
\input{appendix/appendix}
\input{appendix/proofs}

\end{document}