---
title: Agentic Finance: Building, Training and Governing Autonomous Agents in Financial Markets
url: https://www.ml-quant.com/papers/ssrn/7697398/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-11-20
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7697398
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7697398
featured: 2026-11-20
citations: unknown
topic: ML & AI Methods
---


# Agentic Finance: Building, Training and Governing Autonomous Agents in Financial Markets

A practical guide to building and training large language model and reinforcement-learning agents for trading, covering guardrails, learning methods, and multi-agent market dynamics including herding and flash crashes.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7697398
- Identifier: SSRN 7697398
- Released: 2026-11-17
- First featured: Quant Letter No. 140 (2026-11-20): https://www.ml-quant.com/issues/2026-11-20/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods
- Authors: Irene Aldridge

## Related

- [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.
- [Can Generative AI agents behave like humans? Evidence from laboratory market experiments](https://www.ml-quant.com/papers/arxiv/2505.07457/): Large Language Models (LLMs) have potential in mimicking human behavior in economic markets, but need more research for improved diversity and accuracy.
- [LLM Trading Agents Earn Beta, Not Alpha: A Look-Ahead-Free Benchmark](https://www.ml-quant.com/papers/arxiv/2611.19530/): A look-ahead-free benchmark of six language-model traders across three markets finds no significant alpha; market exposure explains 78% of returns and agent decisions match random sector picks.
- [Artificial Intelligence and Generative AI in Asset Management Large Language Models, Autonomous Agents and the Information Efficiency of Equity Markets](https://www.ml-quant.com/papers/ssrn/7718103/): The study argues that large language models lower the cost of processing public text, accelerating price discovery and shortening post-announcement drifts in equity markets.
- [BuySideFlow: A Point-in-Time Benchmark for LLM Agents in Investment Research](https://www.ml-quant.com/papers/arxiv/2611.12966/): Evaluates LLM agents on 408 investment research tasks, finding that half of workflows passing result checks contain temporal violations, revealing a 50.8% gap between output agreement and temporal validity.
