{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:15:39Z","timestamp":1779282939114,"version":"3.51.4"},"reference-count":0,"publisher":"Politechnika Wroclawska Oficyna Wydawnicza","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["EISEJ"],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:p>Context: Recent advances in LLM-based diagram generation increasingly rely on coordinated agent systems rather than single-model prompts.<\/jats:p>\n                  <jats:p>Objective: This work highlights how modular multi-agent architectures improve reliability, semantic grounding, and iterative refinement in text-to-diagram workflows.<\/jats:p>\n                  <jats:p>Method: We analyze a pipeline composed of specialized agents for interpretation, synthesis, validation, and correction, each contributing a bounded and inspectable transformation.<\/jats:p>\n                  <jats:p>Results: The agent system provides deterministic validation, structured reasoning, and controlled refinement loops that outperform monolithic LLM generation.<\/jats:p>\n                  <jats:p>Conclusions: Multi-agent LLM pipelines represent a robust foundation for precise, verifiable diagram generation and serve as a reproducible alternative to single-pass text-to-diagram models.<\/jats:p>","DOI":"10.37190\/e-inf260109","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:04:10Z","timestamp":1779282250000},"page":"260109","source":"Crossref","is-referenced-by-count":0,"title":["A Modular Multi-Agent {LLM} Architecture for Text-to-Diagram Generation and User-Guided Refinement"],"prefix":"10.37190","volume":"20","author":[{"given":"Hartwig","family":"Grabowski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"23140","published-online":{"date-parts":[[2026]]},"container-title":["e-Informatica Software Engineering Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.e-informatyka.pl\/EISEJ\/papers\/2026\/1\/9\/eInformatica2026Art09.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:04:10Z","timestamp":1779282250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.e-informatyka.pl\/EISEJ\/papers\/2026\/1\/9\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026]]},"published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.37190\/e-inf260109","relation":{},"ISSN":["2084-4840"],"issn-type":[{"value":"2084-4840","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}