SPB Git forge

spb/wp13_uqo

Public
3commits 1branches 1releases
1.2 MBsize
maindefault branch
4 h agolast push
TeX 93.9% Python 6%
2.1 KB · 37 lines latex
Raw Blame History
1\begin{table}[htbp]2\centering3\caption{Taxonomy of the tool catalogue exposed to the model. VQuant defines more than two4hundred tools through a schema-driven function-calling protocol. Counts are approximate and5group conceptually related endpoints; the financial families are backed by a market-data6provider exposing over 265 endpoints, wrapped by roughly 230 typed server functions.}7\label{tab:tools}8\begin{threeparttable}9\begin{tabular}{@{}lll@{}}10\toprule11Family & Count & Representative tools \\12\midrule13Company fundamentals      & 40+ & profile, income statement, balance sheet, cash flow, ratios \\14Market data               & 30+ & quote, historical / intraday prices, market movers, batch quote \\15Technical analysis        & 8+  & RSI, MACD, EMA/SMA, ADX, CCI, stochastic, Williams \%R \\16Analyst and ratings       & 20+ & estimates, price targets, upgrades/downgrades, rating history \\17Insider and institutional & 15+ & insider trades, 13F filings, congressional/senate trading \\18Economic and macro        & 15+ & treasury rates, indicators, calendar, COT reports \\19Forex and crypto          & 15+ & FX and crypto quotes, lists, historical series, commodities \\20SEC and compliance        & 25+ & filings by form type, company notes, call transcripts \\21Events and calendars      & 10+ & earnings, dividends, splits, IPO calendar and disclosures \\22ESG and alternative       & 20+ & ESG scores, social sentiment, headcount, executive pay \\23Options                   & 4   & option chain, prices, Greeks, volatility surface \\24Advanced analysis         & 7   & Monte Carlo, Black--Scholes, custom Python, bulk download \\25Web research              & 6   & scrape, crawl, extract; AI / semantic / engine search \\26\bottomrule27\end{tabular}28\begin{tablenotes}[flushleft]29\footnotesize30\item \textit{Notes.} The system prompt instructs the model to select tools according to query31complexity (Section~\ref{subsec:routing}); the most powerful entries---Monte Carlo simulation,32option pricing, and arbitrary Python execution---are described in detail in33Section~\ref{sec:capabilities}.34\end{tablenotes}35\end{threeparttable}36\end{table}37