https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/Head https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/assertion https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/provenance https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/pubinfo https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/assertion https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/dc/terms/title M 3 KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GraphRAG https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#HippoRAG2 https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#LightRAG https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#M2ConceptBase https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#MRMKG https://doi.org/10.48550/arXiv.2512.20136 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#VATKG https://doi.org/10.48550/arXiv.2512.20136 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.w3.org/ns/prov#Entity https://neverblink.eu/ontologies/llm-kg/methods#GraphRAG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GraphRAG http://www.w3.org/2000/01/rdf-schema#label GraphRAG https://neverblink.eu/ontologies/llm-kg/methods#HippoRAG2 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#HippoRAG2 http://www.w3.org/2000/01/rdf-schema#label HippoRAG2 https://neverblink.eu/ontologies/llm-kg/methods#LightRAG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#LightRAG http://www.w3.org/2000/01/rdf-schema#label LightRAG https://neverblink.eu/ontologies/llm-kg/methods#M2ConceptBase http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#M2ConceptBase http://www.w3.org/2000/01/rdf-schema#label M2ConceptBase https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG http://www.w3.org/2000/01/rdf-schema#comment M3KG-RAG is an end-to-end framework that constructs a multi-hop multimodal knowledge graph (M3KG) using a lightweight multi-agent pipeline (LLMs as agents for KG construction) and employs a novel Grounded Retrieval And Selective Pruning (GRASP) mechanism for retrieving and filtering knowledge. It is designed to enhance multimodal large language models (MLLMs) by supplying query-aligned, answer-supportive knowledge to improve their reasoning depth and answer faithfulness. This method integrates LLM agents for KG construction and KG-enhanced retrieval for MLLMs, thereby synergizing both aspects for reasoning. https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG http://www.w3.org/2000/01/rdf-schema#label M3KG-RAG (Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation) https://neverblink.eu/ontologies/llm-kg/methods#M3KGRAG https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG https://neverblink.eu/ontologies/llm-kg/methods#MRMKG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#MRMKG http://www.w3.org/2000/01/rdf-schema#label MR-MKG https://neverblink.eu/ontologies/llm-kg/methods#VATKG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#VATKG http://www.w3.org/2000/01/rdf-schema#label VAT-KG https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/provenance https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2512.20136 https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/pubinfo https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://purl.org/dc/terms/created 2026-02-26T16:25:19.285Z https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2512.20136 https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/sig http://purl.org/nanopub/x/hasSignature TOsKO1xEtmLIE66dS8jTC33Z7kWnCWwBOBEs/ux9Z5HFAUJjfTgjWzjEoWb6KYEC3czSeynusALBOutncCe2zCu7Jm+Oih0NcczBkvt9ZRQubWB/F8Kpg9D5H7sVxQ63n/fuSDEMQIBQm4gZurzO89HDfe7U1LriC3Q7W/xLQu8Y2ItiqKTVLufKR7zgE5qGhOqHow5ewjabs5NGlRI7YraOgFtungOSzx+7/THlHJWeaYU+Kfk76UPoiqJOHFepTaHQatfGtvYuBl7dMtWikRozazhhGzM5GkekhiMW1jHV+hORqHxeDG+q9Bbx0YUw81q//gia7EYN3X/dkoR1vA== https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0 https://w3id.org/np/RAhqhJYaWKp4uVM8DekNlbg482M_2J7ItjydcrtFGcFD0/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent