Search papers, labs, and topics across Lattice.
This paper tackles the challenge of automatic schema generation for ship maintenance reports by introducing ASMR, a modular framework with two specialized agents. The Field Generation Agent extracts semantic concepts and generates candidate schema fields using adaptive multi-granularity clustering, while the Structural Optimizer Agent employs reinforcement learning to refine these schemas into compact and informative representations. The resulting schemas enhance report quality by guiding authors toward more complete and consistent documentation, revealing significant potential for improving operational efficiency in maritime contexts.
Compact and informative schemas generated by ASMR can revolutionize the way ship maintenance reports are authored, leading to more actionable insights.
In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, 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. A Field Generation Agent extracts semantic concepts from historical narratives and generates candidate schema fields through adaptive multi-granularity clustering, while a 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.
