collaborators

6 papers

cs.AI2026

From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generation

Hamied Nabizada, Thomas Wirt, Luis Miguel Vieira da Silva +2

Engineers designing production systems need to verify that a given layout supports all required production sequences. Automated planning techniques can answer such questions, but f…

cs.AI2026

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

Luis Miguel Vieira da Silva, Nicolas König, Felix Gehlhoff

In modern industry, dynamic environments and the complexity of modular and reconfigurable resources require automated planning of process sequences. Capability-based planning appro…

cs.AI2026

Arbor: A Framework for Reliable Navigation of Critical Conversation Flows

Luís Silva, Diogo Gonçalves, Catarina Farinha +2

Large language models struggle to maintain strict adherence to structured workflows in high-stakes domains such as healthcare triage. Monolithic approaches that encode entire decis…

cs.SE2025

Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff

Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often res…

cs.AI2025

Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces

Luis Miguel Vieira da Silva, Aljosha Köcher, Nicolas König +2

Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a mac…

cs.AI2025

Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol

Niklas Jobs, Luis Miguel Vieira da Silva, Jayanth Somashekaraiah +3

Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potent…