# ASMR: Agentic Schema Generation for Ship Maintenance Report Writing

arXiv: https://arxiv.org/abs/2607.08177 · HTML: https://mlsanity.com/paper/2607.08177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 9 of 9)

- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing](https://mlsanity.com/paper/2410.12189/) (2024)
- [A Declarative System for Optimizing AI Workloads](https://mlsanity.com/paper/2405.14696/) (2024)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [Schema-Guided Natural Language Generation](https://mlsanity.com/paper/2005.05480/) (2020)
- [Schema Generation for Large Knowledge Graphs Using Large Language Models](https://mlsanity.com/paper/2506.04512/) (2025)
- [AI-assisted JSON Schema Creation and Mapping](https://mlsanity.com/paper/2508.05192/) (2025)
- [Generative Ontology: When Structured Knowledge Learns to Create](https://mlsanity.com/paper/2602.05636/) (2026)
- [Efficient Learned Query Execution over Text and Tables [Technical Report]](https://mlsanity.com/paper/2410.22522/) (2024)

## Abstract (arXiv)

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.