ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning

Abstract: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.

6 pages, 6 figures. Accepted at the 12th IEEE International Conference on Sustainable Technologies and Engineering (IEEE iCOSTE 2026), Cox's Bazar, Bangladesh, November 1-3, 2026

Machine Learning (cs.LG)

arXiv:2610.23618 [cs.LG]

(or arXiv:2610.23618v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.23618 arXiv-issued DOI via DataCite (pending registration)