An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning
Luis Miguel Vieira da Silva, Nicolas K\"onig, Felix Gehlhoff
Why It Matters
What makes this one worth your time
This work is relevant for AI engineers and researchers interested in enhancing the flexibility and user-friendliness of automated planning systems in dynamic industrial environments.
A hybrid system combining LLMs with SMT planning improves industrial automation adaptability.
Summary
The paper introduces a hybrid assistance system that integrates a Large Language Model (LLM) with a capability-based Satisfiability Modulo Theories (SMT) planning approach to enhance natural-language interaction, explanation, and adaptation in industrial automation. The system is evaluated on a modular production system, demonstrating improved accessibility and adaptability through a combination of formal planning and LLM-based assistance.
Key contributions
- Development of a hybrid assistance system combining LLMs with SMT planning.
- Implementation of a routed agentic workflow with specialized agents for planning tasks.
- Evaluation of the system on a modular production system, demonstrating improved planning outcomes.
Notable insights
- The integration of LLMs with formal planning systems can enhance natural-language interaction and adaptability.
- Human-in-the-Loop (HitL) approval is used for flexible knowledge model adaptation, ensuring user control over automated processes.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2605.28666v1 Announce Type: new 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.