Agentic Trading: When LLM Agents Meet Financial Markets

TL;DR

This paper reviews 77 studies on LLM-based trading agents, highlighting significant reproducibility and evaluation challenges, and proposes an analytical framework emphasizing architecture, capability, and adaptation.

Contribution

It provides an audit-oriented evidence map of existing research, emphasizing reproducibility issues and proposing a new analytical lens for evaluating LLM trading agents.

Findings

Only 2/19 studies report time-consistent split protocols.

Most studies lack explicit transaction-cost models.

Reproducibility remains a major bottleneck in the field.

Abstract

A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decisions, emit tradable actions, and adapt under market feedback. This paper reframes LLM-based trading agents as expert-system decision pipelines and presents an audit-oriented evidence map of 77 included studies in a protocol-coded snapshot screened through 2026-03-09. A primary empirical subset (n=19) satisfies the minimum boundary of Action Output plus Closed-Loop Evaluation; the remaining 58 included studies are retained as background and design context. The central empirical finding is protocol incomparability: within the primary subset, only 2/19 studies report extractable time-consistent split protocols, 1/19 reports an explicit transaction-cost model, 1/19 documents universe or survivorship handling, 11/19 report execution timing or semantics, 15/19 are coded as R0, and no study reaches R3 reproducibility. We therefore use Architecture-Capability-Adaptation as a working analytical lens rather than a validated taxonomy, and we foreground the evidence ledger, reproducibility audit, and reporting checklist as the main contributions. The resulting survey shows that architectural experimentation is expanding rapidly, while comparable evaluation protocols, execution semantics, and reproducible artifacts remain the field's immediate bottlenecks.