Artificial intelligence

TITAN-MoE: Topology-Aware and Predictive Expert Orchestration for Distributed Mixture-of-Experts Inference on Apple Silicon

A Measured Systems Study on a Heterogeneous Mac Cluster

Simon-Pierre Boucher · UQO Working Papers · November 2026 · v0.1

Sparse mixture-of-experts (MoE) language models touch only a few experts per token, so a model whose weights exceed a machine's memory can still be served if the right experts are in the right place at the right time. This preliminary working paper reports the design, implementation and measurement of TITAN-MoE, an…

PRISME: Intervention-Supervised Sparse Workspace Editing for Small Language Models

Design, controlled evaluation, and negative and positive evidence at the 100M-parameter scale

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

PRISME augments a frozen causal decoder with a read-only source bank, an ephemeral sixteen-slot latent workspace re-created at every position, a shared sparse editor that rewrites one or two slots per action, a value controller trained on counterfactual intervention gains measured by executing paired edit/no-edit…

Beyond Text: Cache Compression and Knowledge Transfer in Multi-Agent Systems

A Reproducible Study of Fidelity, Communication Cost, and Repeated Handoffs

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Agents built on language models hand information to one another as text, summaries, structured evidence, shared-memory references or, when they share a checkpoint, attention state (the KV cache). This paper asks under which task, model, cache, network and reuse conditions each representation preserves task-relevant…

Protocol-Guided Autonomous Research with Claude Code

Scientific Verification, Reproducibility, and the Cost of Delegation: A Controlled Study

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Instruction files that steer coding agents through research tasks range from one sentence to several thousand words of phases, gates and integrity rules, but whether that structure changes what the agent delivers has not been measured with the agent held fixed. The paper reports 288 live Claude Code runs (362…

The Invisible Hand of Machines: Price Discovery in Markets Populated by LLM Agents

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

What happens to price discovery when a growing share of the traders in a market are autonomous language-model agents? The paper builds an event-sourced continuous double-auction exchange with exact accounting, a latent dividend process that separates fundamental value from public value and transaction price, seven…

Can Autonomous AI Agents Discover the Fundamental Value of Real Estate? Evidence from Quebec Transactions and Multi-Agent Deliberation

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Committees of role-specialised language-model agents that debate before answering are increasingly proposed as valuation tools. This paper asks 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…

When AI Agents Become Economic Agents: An Agentic General Equilibrium Theory

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Households and firms are beginning to delegate economic decisions to autonomous agents built on a few shared foundation models. This paper studies what this does in general equilibrium. A human's decision error is idiosyncratic and averages out; an AI agent's error is common to every principal that uses the same…

From Listing Images to Property Valuation: A Multimodal AI Framework for Automated Building Characterization and the Cost Approach

Evidence from Québec single-family listings matched to the assessment roll

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

The cost approach to value requires a specification of the improvements — materials, finish grade, condition, renovations — that assessment rolls do not record and that appraisers obtain by inspection. This paper asks whether that specification can be extracted from the photographs and text of a for-sale listing by…

Hedonic House Pricing with Language-Model and Vision Features: Evidence from Quebec Real-Estate Listings

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v2.1

Hedonic house-price models are bounded by the characteristics an analyst can measure, yet much of a home's value is recorded only in the free-text description and photographs of its listing. This paper treats general-purpose AI models as a feature-engineering technology: a large language model converts each…

VQuant: An Agentic Large Language Model Architecture for Automated Quantitative Financial Analysis and Document Generation

Reasoning-Augmented Tool Orchestration, In-Loop Numerical Computation, and Multi-Format Reporting

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.1

Large language models write fluently about finance, but fluency does not make a number correct, current, or reproducible. This paper is a design-science description of VQuant, a deployed web platform that couples a reasoning-capable LLM with a deterministic execution substrate so that a natural-language request…

Does the Language of Artificial Intelligence Move Markets? A Semantic Analysis of Russell 3000 SEC Filings and the Cross-Section of Stock Returns, 2010–2026

Manel Kammoun, Djerrycharli Tandjambianda and Simon-Pierre Boucher · FIRC Research Papers · October 2026 · v2.0

This paper measures artificial-intelligence (AI) engagement in the SEC filings of some 2,500 U.S. listed firms (the current S&P 500 constituents and the holdings of the iShares Russell 3000 ETF) by embedding every passage of their Form 10-K, 10-Q and 8-K filings of 2010–2026 with a sentence transformer and scoring it…

Decoding Real Estate Descriptions: Semantic Embeddings and Hedonic Pricing of Residential Properties in Quebec

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.2

Broker-written listing descriptions contain information about housing quality that structured hedonic variables omit. This paper proposes an interpretable way to use that information: sentence-transformer embeddings of 17,087 single-family listings from Quebec are projected, by cosine similarity, onto 20…

From Corporate Disclosures to a Russell 3000 Strategic Project Database: Identification, Measurement, Validation, and Research Applications

Manel Kammoun, Djerrycharli Tandjambianda and Simon-Pierre Boucher · FIRC Research Papers · October 2026 · v1.0

This paper documents the construction of SPID, a project-level research database that reconstructs the strategic initiatives disclosed by U.S.-listed companies in their SEC filings. Starting from an issuer universe that merges a current S&P 500 snapshot with the holdings of the iShares Russell 3000 ETF (2,564 distinct…