SMARTAPS: Tool-augmented LLMs for Operations Management

2025-07-23

AI Summary

Traditional Advanced Planning Systems (APS) rely on costly consultant-driven customization and maintenance, rendering them inaccessible to small- and medium-sized enterprises (SMEs). Method: This paper introduces the first tool-augmented large language model (LLM) system tailored for operational planning. It enables natural-language-based querying, counterfactual reasoning, recommendation generation, and multi-scenario analysis via a closed-loop interaction framework that integrates semantic understanding, external tool invocation—including optimization solvers—and dynamic collaborative decision-making. Contribution/Results: To our knowledge, this is the first work to adapt tool-augmented LLMs to operational planning, supporting iterative, conversational planning and substantially lowering domain-expertise barriers. Empirical evaluation demonstrates feasibility in supply chain planning tasks. A system demonstration video has been open-sourced.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large language models (LLMs) present intriguing opportunities to enhance user interaction with traditional algorithms and tools in real-world applications. An advanced planning system (APS) is a sophisticated software that leverages optimization to help operations planners create, interpret, and modify an operational plan. While highly beneficial, many customers are priced out of using an APS due to the ongoing costs of consultants responsible for customization and maintenance. To address the need for a more accessible APS expressed by supply chain planners, we present SmartAPS, a conversational system built on a tool-augmented LLM. Our system provides operations planners with an intuitive natural language chat interface, allowing them to query information, perform counterfactual reasoning, receive recommendations, and execute scenario analysis to better manage their operation. A short video demonstrating the system has been released: https://youtu.be/KtIrJjlDbyw

Problem

• Enhance user interaction with traditional algorithms using LLMs
• Reduce costs of advanced planning system customization and maintenance
• Provide intuitive natural language interface for operations management

Innovation

• Tool-augmented LLM for operations management
• Natural language chat interface for planners
• Enables querying and scenario analysis