Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource Planning

2026-07-19

AI Summary

This work addresses the limitations of traditional ERP systems, which rely heavily on manual intervention for exception handling and cross-functional decision-making, suffer from rule-based automation lacking reasoning capabilities, and struggle with monolithic AI approaches that cannot effectively coordinate multi-domain tasks. To overcome these challenges, the authors propose a role-aligned multi-agent LLM architecture featuring a Planner–Executor–Reflector–Responder graph-driven orchestration framework that decouples generation from evaluation. The design incorporates a risk-tiered human-in-the-loop supervision mechanism and externalized scoring criteria, substantially reducing tool selection complexity and yielding auditable expert-system components. Evaluated on real-world ERP backends across end-to-end business processes—including scenario-specific tasks, cross-functional crisis responses, and 365-day simulations—the system significantly outperforms both rule-based RPA and unassisted baselines, achieving zero stockouts compared to hundreds of stockout incidents recorded under baseline conditions.

Abstract

Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot reason about exceptions and monolithic AI assistants degrade when asked to coordinate across functional boundaries. This paper presents Agentic ERP, an expert-system architecture that combines role-aligned large-language-model (LLM) agents with a risk-tiered human-in-the-loop harness and a graph-based orchestrator to execute end-to-end business workflows on a production ERP backend. First, autonomous ERP operation is formulated as a constrained sequential-decision problem over a structured enterprise state, with a decomposition argument linking role-aligned agents to a measurable reduction in per-step tool-selection complexity. Second, a graph-based Planner--Executor--Reflector--Responder orchestration decouples generation from evaluation through externalised grading criteria and sprint contracts, packaging recent harness-engineering principles as inspectable expert-system artefacts. Third, the system is evaluated at three levels: a scenario-based task suite, a comprehensive comparison of six orchestration paradigms on cross-functional crisis tasks, and a 365-day agent-in-the-loop simulation against rule-based RPA and no-intervention baselines. Across these levels the proposed multi-agent method is significantly better than the baseline, and the system sustains a simulated year of operation with zero stockouts while the rule-based baseline accumulates hundreds under the same demand stream. The work shows that role-aligned LLM agents under human oversight can move an ERP system from passively recording transactions to actively executing operational decisions, and it provides a reference architecture and an evaluation protocol for autonomous enterprise resource planning.

Problem

• Enterprise Resource Planning
• operational decision-making
• exception handling
• cross-functional coordination
• autonomous ERP

Innovation

• multi-agent LLM
• role-aligned agents
• graph-based orchestration
• human-in-the-loop
• autonomous ERP