{"paper":{"title":"Vibe-driven model-based engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Vibe coding with LLMs and model-driven engineering can complement each other instead of competing, creating hybrid paths for different software projects and users.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jordi Cabot","submitted_at":"2026-04-12T13:47:06Z","abstract_excerpt":"There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability concerns, etc. bring new challenges that we need to handle. In the last years, model-driven engineering (MDE), including its latest incarnation, i.e. low/no-code development, has been key to improving the quality and productivity of software development, but models themselves are becoming increasingly complex to specify and manage. At the same time, we are witness"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we argue that, in fact, the two approaches can complement each other and provide altogether different development paths for different types of software systems, development scenarios, and user profiles. In this sense, we introduce the concept of vibe-driven model-based engineering as a novel approach to integrate the best of both worlds (AI and MDE) to accelerate the development of reliable complex systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the vulnerabilities, scalability issues, and maintainability concerns of LLM-based vibe coding can be mitigated through integration with MDE without adding new complexities to model specification and management.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Vibe-driven model-based engineering integrates LLM natural-language coding with model-driven engineering to accelerate development of reliable complex systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vibe coding with LLMs and model-driven engineering can complement each other instead of competing, creating hybrid paths for different software projects and users.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"aaeca3d55fc6c1141212a71cb5659b1730d882959ceb7f7e9697f333299f2421"},"source":{"id":"2604.10645","kind":"arxiv","version":2},"verdict":{"id":"fcf25a20-a68b-45da-bbf0-ea76f65fa62c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:47:22.174091Z","strongest_claim":"we argue that, in fact, the two approaches can complement each other and provide altogether different development paths for different types of software systems, development scenarios, and user profiles. In this sense, we introduce the concept of vibe-driven model-based engineering as a novel approach to integrate the best of both worlds (AI and MDE) to accelerate the development of reliable complex systems.","one_line_summary":"Vibe-driven model-based engineering integrates LLM natural-language coding with model-driven engineering to accelerate development of reliable complex systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the vulnerabilities, scalability issues, and maintainability concerns of LLM-based vibe coding can be mitigated through integration with MDE without adding new complexities to model specification and management.","pith_extraction_headline":"Vibe coding with LLMs and model-driven engineering can complement each other instead of competing, creating hybrid paths for different software projects and users."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10645/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}