Metraipolis › archive › dc_994bc66c5cd3
ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning — arXiv:2610.23618
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23618
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:10:21.753Z
- SHA-256 of the archived text
618cd3f935ff4537ec5dd7852f8c3e2b43f111d57a0e610962c3d307a107f690- Stable URL of this page
https://metraipolis.com/documento/dc_994bc66c5cd3
How to cite
ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning — arXiv:2610.23618 — arXiv (en), https://arxiv.org/abs/2610.23618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_994bc66c5cd3 (Metraipolis archive dc_994bc66c5cd3, sha256 618cd3f935ff4537ec5dd7852f8c3e2b43f111d57a0e610962c3d307a107f690)
BibTeX
@misc{dc994bc66c5cd3,
title = {ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning — arXiv:2610.23618},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23618},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_994bc66c5cd3; sha256 618cd3f935ff4537ec5dd7852f8c3e2b43f111d57a0e610962c3d307a107f690},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Staging a theatre performance requires coordinating dialogue, actor movement, stage directions, lighting focus, cue timing, and equipment constraints within the same production plan. This work presents ThetreStageAI, a retrieval augmented framework for structured Bengali theatre production planning. Rather than retrieving from one mixed corpus, the system maintains separate scene, actor-blocking, and lighting views. Bengali text is embedded with BGE-M3 and indexed in view-specific Qdrant collections. Retrieved references are combined with a production brief and passed to Gemini, which generates schema-constrained JSON containing characters, scenes, dialogue, stage directions, blocking, lighting, and optional sound cues. Structural and semantic checks are applied before acceptance, with at most one constrained repair attempt. We also construct a human-guided, LLM-assisted synthetic dataset of 500 short Bengali theatre records that expands to 1,500 retrieval documents. Dataset diagnostics confirm consistent identifiers and valid lighting fields while also revealing substantial dialogue repetition. A paired camera-ready evaluation compares single-combined and full multi-view retrieval under matched settings. The source code, dataset, and evaluation materials are publicly available. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.23618 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:06:29.560Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).