Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Phat, Pham, Thang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914429891772416
author Nguyen, Phat
Pham, Thang
author_facet Nguyen, Phat
Pham, Thang
contents Multi-agent systems based on large language models (LLMs) for financial trading have grown rapidly since 2023, yet the field lacks a shared framework for understanding what drives performance or for evaluating claims credibly. This survey makes three contributions. First, we introduce a four-dimensional taxonomy, covering architecture pattern, coordination mechanism, memory architecture, and tool integration; applied to 12 multi-agent systems and two single-agent baselines. Second, we formulate the Coordination Primacy Hypothesis (CPH): inter-agent coordination protocol design is a primary driver of trading decision quality, often exerting greater influence than model scaling. CPH is presented as a falsifiable research hypothesis supported by tiered structural evidence rather than as an empirically validated conclusion; its definitive validation requires evaluation infrastructure that does not yet exist in the field. Third, we document five pervasive evaluation failures (look-ahead bias, survivorship bias, backtesting overfitting, transaction cost neglect, and regime-shift blindness) and show that these can reverse the sign of reported returns. Building on the CPH and the evaluation critique, we introduce the Coordination Breakeven Spread (CBS), a metric for determining whether multi-agent coordination adds genuine value net of transaction costs, and propose minimum evaluation standards as prerequisites for validating the CPH.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27539
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness
Nguyen, Phat
Pham, Thang
Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
Multi-agent systems based on large language models (LLMs) for financial trading have grown rapidly since 2023, yet the field lacks a shared framework for understanding what drives performance or for evaluating claims credibly. This survey makes three contributions. First, we introduce a four-dimensional taxonomy, covering architecture pattern, coordination mechanism, memory architecture, and tool integration; applied to 12 multi-agent systems and two single-agent baselines. Second, we formulate the Coordination Primacy Hypothesis (CPH): inter-agent coordination protocol design is a primary driver of trading decision quality, often exerting greater influence than model scaling. CPH is presented as a falsifiable research hypothesis supported by tiered structural evidence rather than as an empirically validated conclusion; its definitive validation requires evaluation infrastructure that does not yet exist in the field. Third, we document five pervasive evaluation failures (look-ahead bias, survivorship bias, backtesting overfitting, transaction cost neglect, and regime-shift blindness) and show that these can reverse the sign of reported returns. Building on the CPH and the evaluation critique, we introduce the Coordination Breakeven Spread (CBS), a metric for determining whether multi-agent coordination adds genuine value net of transaction costs, and propose minimum evaluation standards as prerequisites for validating the CPH.
title Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness
topic Multiagent Systems
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2603.27539