Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)

2026-05-18

AI Summary

This study addresses the inadequacy of existing knowledge graph metadata standards in characterizing agent reasoning capabilities, which hinders accurate selection, composition, and failure diagnosis of graphs during planning. To bridge this gap, the paper introduces the Agentic Affordance Profile (AAP)—a four-dimensional formal semantic layer that, for the first time, adapts service-oriented ontological commitments and capability descriptions to the knowledge graph domain. Built upon description logic and extending established metadata frameworks such as VoID and DCAT, AAP enables semantic grounding of task vocabularies, closed-world assumptions for empty query results, and formal representation of derivable knowledge. This framework fills a critical theoretical void in agent–graph capability alignment and outlines a five-point research agenda to support its large-scale deployment.

Abstract

Two decades ago, the Semantic Web Services community was asked how agents with different ontological commitments could discover, compose, and invoke web services coherently. The response was OWL-S and WSMO: formally grounded capability descriptions specifying what a service could do, what the agent must already know for invocation to be epistemically sound, and how ontological mismatches could be formally bridged. Current Knowledge Graph (KG) metadata standards such as VoID and DCAT describe what a KG contains yet say nothing about what a specific agent can prove from it, what closure assumptions govern empty results, or whether the agent's task vocabulary is grounded in the schema. Furthermore, in deployed KGs the governing schema DL and the operative entailment regime can diverge: an epistemic failure mode invisible to current metadata. We revisit and extend these insights for the KG setting with a four-dimensional formal framework from which we derive the Agentic Affordance Profile (AAP): a semantic layer above VoID and DCAT enabling principled KG selection, composition, and failure diagnosis at agent planning time. A five-point research agenda identifies the formal, computational, and engineering work needed to realise AAP-based affordance matching at scale.

Problem

• Knowledge Graph
• Agent Affordance
• Semantic Metadata
• Ontological Mismatch
• Epistemic Soundness

Innovation

• Agentic Affordance Profile
• Knowledge Graph Metadata
• Formal Framework
• Epistemic Alignment
• Semantic Interoperability