← 研踪 PaperTrailarXiv:2611.20333 · v1
Beyond Service Discovery: Coverage Awareness in LLM-Driven Service Composition
首次提交 2026-11-16 07:54
版本更新 2026-11-16 07:54
雷达观测 2026-11-17 17:12
摘要
Large language models increasingly support the automated discovery and composition of services. In federated data ecosystems, this creates new opportunities for reusing existing data products and transformation services when constructing service-based data exchange modeled as data-sharing pipelines. However, finding relevant reusable assets does not imply that the available assets are sufficient to satisfy a consumer request. In this paper, we distinguish reuse discovery, the ability to identify relevant published assets, from reuse coverage, the extent to which the available assets support the transformations required by a request. We further consider coverage awareness, the ability of a composition system to recognize insufficient coverage. We investigate this distinction using PipeFinder, an LLM-driven framework for composing data-sharing pipelines, and evaluate 99 consumer requests against a fixed catalogue of data products and transformation services. Our experiments show that relevant data products can be discovered reliably, while successful composition remains considerably more difficult. More importantly, when required transformation services are missing, the framework typically constructs a pipeline from the available services rather than recognizing that the request cannot be satisfied. Explicitly incorporating coverage checking into the planning procedure substantially improves recognition of such cases. These results suggest that coverage awareness should be treated as an explicit concern in LLM-driven service composition and cannot be assumed to follow from improved discovery or model capability.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 07:54 · 最新观测版本
Beyond Service Discovery: Coverage Awareness in LLM-Driven Service Composition
Large language models increasingly support the automated discovery and composition of services. In federated data ecosystems, this creates new opportunities for reusing existing data products and transformation services when constructing service-based data exchange modeled as data-sharing pipelines. However, finding relevant reusable assets does not imply that the available assets are sufficient to satisfy a consumer request. In this paper, we distinguish reuse discovery, the ability to identify relevant published assets, from reuse coverage, the extent to which the available assets support the transformations required by a request. We further consider coverage awareness, the ability of a composition system to recognize insufficient coverage. We investigate this distinction using PipeFinder, an LLM-driven framework for composing data-sharing pipelines, and evaluate 99 consumer requests against a fixed catalogue of data products and transformation services. Our experiments show that relevant data products can be discovered reliably, while successful composition remains considerably more difficult. More importantly, when required transformation services are missing, the framework typically constructs a pipeline from the available services rather than recognizing that the request cannot be satisfied. Explicitly incorporating coverage checking into the planning procedure substantially improves recognition of such cases. These results suggest that coverage awareness should be treated as an explicit concern in LLM-driven service composition and cannot be assumed to follow from improved discovery or model capability.
查看此版本解读 →查看此版本原文 ↗