In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, we seek to automatically discover compact and informative schemas that capture the essential information requirements of each report type. To address this challenge, we propose ASMR, a modular agentic framework consisting of two specialized agents.
First, the Field Generation Agent extracts semantic concepts from historical narratives and generates candidate schema fields through adaptive multi-granularity clustering. Second, the Structural Optimizer Agent employs reinforcement learning to identify compact, informative, and non-redundant schema representations. The resulting schemas can guide report authors toward producing more complete, consistent, and actionable reports.
Preliminary results demonstrate the promise of the proposed approach and highlight several open research challenges at the intersection of data management, agentic AI, and human-centered AI.
Blogger's Review: The ASMR framework offers a novel approach to automating ship maintenance reporting by integrating intelligent agents and reinforcement learning. Future research could expand its applications and improve human-agent collaboration efficiency. The challenges in schema generation accuracy and adaptability are particularly noteworthy in this field.