Skip to content
Open access

FinGraph-MAR: A Graph Retrieval-Augmented Multi-Agent Framework for Intelligent Financial Back-Office Automation and SaaS Revenue Management

Sep 2026 · Fundamental Scientific Reports in Multidisciplinary Areas · Vol 2, pp. 173-190 · 0 citations

TL;DR

Experimental results demonstrate that FinGraph-MAR achieves 95.6% task understanding accuracy, 94.9% F1-score, and 97.1% workflow completion rate, outperforming rule-based RPA, standalone LLM, conventional RAG, LLM+RPA, and Graph RAG+LLM baselines.

Abstract

The increasing complexity of financial back-office operations and SaaS revenue management has created significant challenges for intelligent automation, particularly in transaction processing, billing verification, revenue recognition, compliance monitoring, and operational decision-making. Existing robotic process automation (RPA) systems mainly rely on predefined workflows and struggle to handle dynamic business relationships, heterogeneous financial data, and knowledge-intensive tasks involving customers, contracts, subscriptions, transactions, and regulatory requirements. To address these limitations, this study proposes FinGraph-MAR (Financial Graph-based Multi-Agent Reasoning), a graph retrieval-augmented multi-agent framework for intelligent financial back-office automation and SaaS revenue management. The proposed framework constructs a heterogeneous financial-SaaS knowledge graph to model entities, events, business relationships, and operational rules, and introduces a hybrid graph-semantic retrieval mechanism to provide relationship-aware contextual knowledge for large language model (LLM)-based agents. Furthermore, FinGraph-MAR integrates a multi-agent collaboration architecture consisting of task planning, transaction analysis, revenue management, risk assessment, compliance verification, execution, and audit agents, together with a risk-constrained decision gate for reliable automated operations.  Experimental results on four publicly available datasets, including FinQA, TAT-QA, UCI Online Retail, and IBM Telco Customer Churn, demonstrate that FinGraph-MAR achieves 95.6% task understanding accuracy, 94.9% F1-score, and 97.1% workflow completion rate, outperforming rule-based RPA, standalone LLM, conventional RAG, LLM+RPA, and Graph RAG+LLM baselines. Ablation experiments further confirm the contributions of graph retrieval, multi-agent collaboration, risk gating, and audit feedback.  

Read PDF

Similar papers

Review Open access Oct 2026

A Shared-Task-State-Driven Multi-Agent Framework for Knowledge Graph Construction in Substation Operation and Maintenance

Knowledge graph construction typically involves data preprocessing, entity recognition, relation extraction, knowledge fusion, conflict resolution, and quality assessment. However, heterogeneous documents in substation operation and maintenance (O&M), including technical standards, defect records, work tickets, operati...

Lin-Qing Huang, Wen-Yong Chen, Shu-Jian Yu et al. · 0 citations
#large language models Open access Sep 2026

Retrieval-Augmented Large Language Models for Real-Time Supply Chain Disruption Intelligence and Decision Support

Large language models offer unprecedented analytical capability, but their knowledge is frozen at the last training date — rendering them unusable for organizations whose mission depends on emerging, timely information [1]. This paper argues that retrieval-augmented generation is the missing mechanism that converts LLM...

Sohail Sayed, Nauman Sayed · 0 citations
Dec 2026

Retrieval-Augmented Generation with Knowledge Graphs for Traffic Control Strategy in Highway Networks

Traffic control strategy generation is a core operational task for maintaining safety and efficiency in highway networks; decisions made by traffic control systems should be grounded in traceable evidence while meeting stringent requirements on timeliness and accuracy. However, traditional practice often remains inef...

Feng-Ze Fan, Jing Deng, Jia-Nuo Hao et al. · 0 citations
#artificial intelligence Open access Sep 2026

EnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making

EnterpriseBench is introduced, a benchmark that evaluates LLM agents across this spectrum, from static question answering to dynamic decision-making, and shows that it provides a practical benchmark for evaluating LLM agents in realistic enterprise strategic reasoning and decision-making.

Min Yang, Yi-Chen Pan, Jing-Hua Piao et al. · 2 citations
Open access Sep 2026

LLM and MCP driven e-commerce assistant over graph databases

An architecture for conversational e-commerce that integrates large language models, Model Context Protocol servers, and a Neo4j graph database to enable natural language product discovery is presented.

Andrii Baran, I. Spivak, S. Krepych · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.