QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance

TL;DR

QRAFTI is a multi-agent framework designed to emulate a quantitative research team, facilitating equity factor research through integrated tools, reproducibility, and explainability in empirical financial analysis.

Contribution

It introduces a novel multi-agent system that combines data access, factor construction, and reporting tools for enhanced empirical research in finance.

Findings

Supports replication of established factors

Enables formulation and testing of new signals

Improves performance and explainability with chained tool calls

Abstract

We introduce a multi-agent framework intended to emulate parts of a quantitative research team and support equity factor research on large financial panel datasets. QRAFTI integrates a research toolkit for panel data with MCP servers that expose data access, factor construction, and custom coding operations as callable tools. It can help replicate established factors, formulate and test new signals, and generate standardized research reports accompanied by narrative analysis and computational traces. On multi-step empirical tasks, using chained tool calls and reflection-based planning may offer better performance and explainability than dynamic code generation alone.