An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning

2026-05-27

AI Summary

This work addresses the lack of interpretable feedback in industrial automation capability planning under infeasible conditions and the difficulty in adapting to dynamic operational environments. The paper proposes the first hybrid decision-support system that integrates SMT-based symbolic planning with large language models (LLMs), enabling natural-language explanations of planning outcomes and user-authorized, adaptive updates to the knowledge model. Leveraging a human-in-the-loop mechanism and a routed multi-agent workflow, the system successfully completed all four feasible planning tasks and nine out of ten knowledge queries across 23 test cases. For three out of four infeasible scenarios, it generated actionable repair suggestions, and in five adaptation scenarios, it achieved feasible plans through user-approved knowledge modifications—establishing the first capability planning framework that is interpretable, interactive, iterative, and formally correct.

Abstract

In modern industry, dynamic environments and the complexity of modular and reconfigurable resources require automated planning of process sequences. Capability-based planning approaches address this by automatically generating plans from semantic knowledge models that describe resource functions in a machine-interpretable form. Their practical use, however, remains limited: solver feedback, especially in the case of unsatisfiability, is difficult to interpret, and the knowledge models require adaptation as operational conditions change or requests become infeasible. This paper presents a hybrid assistance system that augments an existing capability-based Satisfiability Modulo Theories (SMT) planning approach with an Large Language Model (LLM)-based layer for natural-language interaction, explanation, and adaptation. Formal planning correctness remains with the symbolic planner, while the LLM layer handles natural-language access and flexible knowledge model adaptation under explicit Human-in-the-Loop (HitL) approval. The system decomposes into four components: Capability Grounding, Symbolic Planning, Result Interpretation, and Planning Adaptation, realized as a routed agentic workflow in which a central router delegates to five specialized agents. The system is evaluated on a modular production system across four scenario types. Of 23 test cases, 9 of 10 knowledge queries and all 4 satisfiable planning cases were handled correctly, 3 of 4 unsatisfiable cases produced concrete repair proposals, and all 5 adaptive planning scenarios resolved into satisfiable plans through iterative, user-approved knowledge model modifications. The findings confirm that combining formal planning with LLM-based assistance substantially improves accessibility and adaptability in industrial automation.

Problem

• capability-based planning
• industrial automation
• knowledge model adaptation
• SMT planning
• unsatisfiability feedback

Innovation

• Large Language Model
• Capability-Based Planning
• Satisfiability Modulo Theories
• Human-in-the-Loop
• Agentic Workflow