---
title: Agentic AI for Quantitative Investment Research: A Practitioner's Guide
url: https://www.ml-quant.com/papers/ssrn/7683994/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-11-14
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7683994
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7683994
featured: 2026-11-13
citations: unknown
topic: ML & AI Methods
---


# Agentic AI for Quantitative Investment Research: A Practitioner's Guide

A practitioner's guide proposes a reference architecture for deploying agentic AI systems in quantitative research, balancing flexibility and control through two reasoning components around a deterministic execution core.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7683994
- Identifier: SSRN 7683994
- Released: 2026-11-13
- First featured: Quant Letter No. 139 (2026-11-13): https://www.ml-quant.com/issues/2026-11-13/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods
- Authors: Anna-Helena Mihov, Philip Treleaven

## Related

- [Agentic AI in Automated Markets](https://www.ml-quant.com/papers/arxiv/2610.22522/): Deep reinforcement learning simulates three agent archetypes in automated markets, finding herd-followers generate frequent short stress episodes while manipulators create persistent volatility.
- [Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors](https://www.ml-quant.com/papers/arxiv/2609.27051/): Proposes a statistical referee that judges investment factors proposed by language-model agents using out-of-sample market outcomes, ensuring false-discovery control at any stopping time.
- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://www.ml-quant.com/papers/arxiv/2609.29014/): Proposes a multi-agent system with post-training that automates alpha factor mining locally, using diverse research paths and joint optimization to broaden exploration while maintaining prediction quality.
- [Bounded Normative Equivalence in Human-AI Cooperation: Group Behaviour, Not Partner Labels, Predicts Cooperation under Anonymous Aggregate Feedback](https://www.ml-quant.com/papers/arxiv/2601.20487/): AI agents in group settings can influence cooperation just like humans do, showing that social norms can adjust for both AI and human participants.
- [The Adoption and Usage of AI Agents: Early Evidence from Perplexity](https://www.ml-quant.com/papers/arxiv/2512.07828/): A study of AI agent use with the Comet browser reveals that personal productivity and learning are the main reasons users interact with these tools.
- [General Social Agents](https://www.ml-quant.com/papers/arxiv/2508.17407/): Modern AI agents can be used to apply social science theories to new settings with little or no modification, and have been found to predict human behavior more accurately than traditional methods in a sample of new games.