TeX 93.9%
Python 6%
1<!-- Author: Simon-Pierre Boucher — simon-pierre.boucher@uqo.ca -->2# 🤖 VQuant: An Agentic Large Language Model Architecture for Automated Quantitative Financial Analysis and Document Generation34**UQO Working Paper No. 13** — *Reasoning-Augmented Tool Orchestration, In-Loop Numerical Computation, and Multi-Format Reporting*56[-b31b1b?logo=latex&logoColor=white)](paper/main.pdf)7[](paper/main.tex)8[-4051b5)](#-data)9[](https://uqo.ca)10[](mailto:simon-pierre.boucher@uqo.ca)1112> **TL;DR** — VQuant is a production web platform that turns a natural-language request into a13> complete, reproducible quantitative financial report. A reasoning-augmented LLM acts as planner14> and synthesizer; all numerical work is delegated to a deterministic execution substrate: an15> agentic orchestration loop over 200+ tools (265+ market-data endpoints, four web-research16> services, a 17-library Python sandbox), a two-stage context-management algorithm for unbounded17> conversations, a single-call computation paradigm (data → estimation → figures in one sandboxed18> execution), and a unified document pipeline emitting PDF, DOCX, Beamer and spreadsheets with live19> formulas from one Markdown artifact. The paper documents each mechanism as implemented so the20> design can be reproduced.2122---2324## 📌 Status2526| Item | Value |27|---|---|28| Version | 1.0 (June 2026) |29| SSRN | not yet submitted |30| Journal | — |31| Code & data | methodology / system paper — no empirical pipeline; the platform's source code lives in the spbgit repository `vquant.git` |3233## 🎯 What this paper does3435Large language models are fluent in financial discourse, but fluency does not guarantee36numerically rigorous, reproducible or citable analysis. This paper describes the **architecture**37of VQuant, a platform that couples a reasoning-augmented LLM with a deterministic execution38substrate, and argues that the resulting design pattern — *the model plans and synthesizes, auditable39code computes* — is reusable beyond finance.4041Four mechanisms are documented at implementation level:42431. an **agentic orchestration loop** exposing 200+ financial and analytical tools through a44 constrained function-calling protocol (recursive tool-calling loop, tool-use/tool-result45 invariant, batched-execution throttle);462. a **context-management algorithm** preserving coherence over effectively unbounded histories47 via adaptive summarization under a token budget (two-stage machinery, token-accounting correction);483. a **single-call computation paradigm** that consolidates data acquisition, estimation and figure49 rendering into one sandboxed Python execution (inter-process sandbox that exec's model-authored50 code and captures its figures);514. a **unified document pipeline** emitting PDF, DOCX, LaTeX Beamer decks and spreadsheet workbooks52 with live formulas from a single Markdown artifact, streamed through a Server-Sent-Event protocol53 with eight-way event dispatch.5455The classical quantitative methods the platform automates are conventional and relegated to the appendix.5657## 🏆 Headline results5859| Object | Value |60|---|---|61| Tools exposed to the model | 200+ (265+ market-data endpoints, 4 web-research services, Python sandbox) |62| Scientific libraries in the sandbox | 17 |63| Model round trips per computation | 1 (single-call paradigm) vs. several in a naïve agent |64| Output formats from one artifact | PDF, DOCX, Beamer, XLSX (live formulas) |65| Streaming protocol | SSE, 8 event types |6667## 🗂 Repository layout6869```70vquant-llm-quant-platform/71└── paper/ # main.tex + sections/ + figures/ (TikZ diagrams) + tables/ + appendix/ → main.pdf72 ├── figures/ # architecture, loop, context, sandbox, streaming, docpipeline (TikZ)73 └── tables/ # tools, models, events, robustness74```7576No `src/`, `scripts/` or `data/`: the paper has no empirical pipeline.7778## 🚀 Quick start7980```bash81cd paper && make # latexmk → main.pdf (pdflatex + bibtex, TikZ diagrams compiled inline)82```8384## 🗃 Data8586Not applicable. The paper describes a software system; the platform itself (TypeScript/Python)87is maintained in the spbgit repository `vquant.git` and deployed on the MacLustr cluster.8889## 🔬 Methodology90911. **Architecture description** — components, invariants and protocols are specified as implemented (§3–§4).922. **Mechanism walkthroughs** — orchestration loop, context management, single-call computation, document pipeline (§4).933. **Design evaluation** — qualitative robustness discussion of failure modes and mitigations (§6).944. **Appendix** — the conventional quantitative methods automated by the platform.9596## 🖼 Figures & tables inventory9798| Figure (TikZ) | Content |99|---|---|100| `figures/architecture.tex` | end-to-end platform architecture |101| `figures/loop.tex` | recursive tool-calling loop |102| `figures/context.tex` | two-stage context management |103| `figures/sandbox.tex` | inter-process Python sandbox |104| `figures/streaming.tex` | SSE event dispatch |105| `figures/docpipeline.tex` | unified document pipeline |106107Tables (`paper/tables/*.tex`): tool catalogue, models, streaming events, robustness.108109## ⚠️ Limitations110111- Descriptive system paper: no benchmark against alternative agent frameworks is reported.112- Tool counts and endpoint inventories reflect the platform as of June 2026.113- Reproducibility of the *design* is documented; reproducing the *platform* requires the private `vquant.git` code base and API keys.114115## 📝 Citation116117```bibtex118@techreport{boucher2026vquant,119 author = {Boucher, Simon-Pierre},120 title = {VQuant: An Agentic Large Language Model Architecture for Automated Quantitative Financial Analysis and Document Generation},121 institution = {Universit\'e du Qu\'ebec en Outaouais, D\'epartement des sciences administratives},122 type = {Working Paper},123 number = {13},124 year = {2026},125 month = {June}126}127```128129## 👤 Author & contact130131**Simon-Pierre Boucher** — Département des sciences administratives,132Université du Québec en Outaouais (UQO), Gatineau, QC.133📧 [simon-pierre.boucher@uqo.ca](mailto:simon-pierre.boucher@uqo.ca)134135## 🗒 Notes136137- Numbering: first circulated as “Working Paper No. 10” (June 2026); renumbered **13** on 2026-10-17 because No. 10 is *The Assessment Gap in Quebec* (see `Recherche-UQO/HARMONISATION.md`).138- Cover date normalised from “June 13, 2026” to “June 2026”.139- The VQuant platform code is not in this repository (spbgit `vquant.git`).140