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

Terry R. Payne, Valentina Tamma, Enrico Daga

arXiv:2605.19186 · 2026-05-20 공개 · arXiv · PDF

knowledge-graph formal-framework ontology-matching semantic-web affordance-profile agent-knowledge kg-metadata entailment-regime

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.

한국어 요약

한 줄 요약

**[지식 그래프 / 에이전트 인식론]** 에이전트가 KG에서 무엇을 증명할 수 있는지·빈 결과의 폐쇄 가정·태스크 어휘 grounding을 명세하는 4차원 형식 프레임워크 AAP(Agentic Affordance Profile) 제안.

핵심 기여도

핵심 아이디어

"KG가 무엇을 담고 있는가"와 "에이전트가 그 KG에서 무엇을 안전하게 추론·계획할 수 있는가"는 다른 질문이며, 후자는 closure 가정·entailment regime·태스크 어휘 grounding을 명시한 별도의 affordance layer로만 답할 수 있다.

기술적 접근법

주요 결과

의의 및 한계

**의의**: 에이전트가 데이터·지식 자산을 안전하게 활용하기 위한 메타데이터 표준 진화 방향을 제시, semantic web 유산을 LLM 에이전트 시대에 재해석. **한계**: 산업적 채택까지의 거리, 대규모 KG에 대한 AAP 작성 비용·자동화 도구 부재는 후속 작업의 핵심.

실용적 활용