{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:07:45Z","timestamp":1789078065359,"version":"build-2803163510"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686868","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,2]]},"abstract":"<jats:p>Knowledge Graph Question Answering (KGQA) over Large Language Models (LLMs) increasingly translates natural-language questions into SPARQL, yet most systems are statically optimized for a single benchmark and degrade abruptly under cross-domain transfer or schema evolution. We present HARP (Hybrid Agentic-Retrieval Pipeline), a KG-agnostic Text2SPARQL architecture that operates without task-specific fine-tuning. A meta-controller orchestrates a ReAct agent and an execution-validated, schema-guided fallback pipeline. Both paths are grounded by a runtime FAISS-indexed Schema-Discovery service that absorbs structural change by building temporary indices from live SPARQL probes. The system is evaluated across four heterogeneous KGs: DBpedia, a structurally complex Corporate dataset, and two versions of a proprietary railway metadata KG (TrackVideo). The v1 to v2 transition of TrackVideo represents radical schema refactoring, allowing us to test true schema-drift resilience. The hybrid architecture attains a highly consistent performance across all datasets, neutralizing the degradations typically caused by schema drift. A multi-model Quorum extension over heterogeneous LLM families further increases reliability, demonstrating that hybrid agentic retrieval with execution-validated routing is a highly viable paradigm for portable KGQA in production-grade settings.<\/jats:p>","DOI":"10.3233\/ssw260014","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:09:24Z","timestamp":1789074564000},"source":"Crossref","is-referenced-by-count":0,"title":["Navigating Schema Drift: Orchestrating Agents and Schema Discovery for Robust, Domain-Specific Knowledge Graph Question Answering"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2377-2152","authenticated-orcid":false,"given":"Anton","family":"Diettrich","sequence":"first","affiliation":[{"name":"Leipzig University of Applied Sciences (Leipzig, Germany)"},{"name":"DB Systel GmbH (Frankfurt, Germany)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4625-2030","authenticated-orcid":false,"given":"Dirk","family":"Friedenberger","sequence":"additional","affiliation":[{"name":"DB Systel GmbH (Frankfurt, Germany)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9177-5463","authenticated-orcid":false,"given":"Andreas","family":"Both","sequence":"additional","affiliation":[{"name":"Leipzig University of Applied Sciences (Leipzig, Germany)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Studies on the Semantic Web","Bridging the Gap Between Curated and Induced Semantics"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SSW260014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:09:24Z","timestamp":1789074564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SSW260014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"ISBN":["9781643686868"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/ssw260014","relation":{},"ISSN":["1868-1158","2215-0870"],"issn-type":[{"value":"1868-1158","type":"print"},{"value":"2215-0870","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]}}}