A Neurosymbolic Prolog Skill for LLM-Driven Service Placement

2026-06-09

AI Summary

This work addresses the challenge of service placement in cloud-edge continuums, where application components must be allocated to heterogeneous resources under multiple constraints such as latency, physical location, and policy compliance. Existing approaches either rely on explicit modeling or lack transparency and formal guarantees. To overcome these limitations, the paper proposes a neuro-symbolic method that integrates Prolog as a reusable skill interface into large language model (LLM)-driven service placement for the first time. The LLM translates high-level placement intents into structured symbolic facts and rules, which Prolog then processes through logical inference and verification. By synergistically combining semantic understanding with formal reasoning, this approach enables policy-aware, inspectable, and formally verifiable decision-making, thereby supporting compliant and efficient service deployment in cloud-edge environments.

Abstract

Service placement in the cloud-edge continuum requires assigning application components to heterogeneous resources under multiple constraints, including latency, locality, and policy requirements. Existing approaches rely on optimisation models or heuristics that require explicit modelling, while neural methods lack transparency and formal guarantees. This work proposes a neuro-symbolic alternative based on a Prolog skill, a reusable interface for schema-constrained fact generation and querying, for constraint-aware placement. The skill enables a language model to structure placement intent into symbolic facts, rules, and queries, while delegating validation and reasoning to Prolog. This design bridges high-level intent and formal constraint evaluation, enabling inspectable and policy-aware placement decisions in cloud-edge environments.

Problem

• service placement
• cloud-edge continuum
• constraint satisfaction
• neurosymbolic reasoning
• resource allocation

Innovation

• neurosymbolic
• Prolog skill
• service placement
• constraint reasoning
• cloud-edge continuum