Semantic API Alignment: Linking High-level User Goals to APIs

TL;DR

This paper proposes Semantic API Alignment (SEAL), a multi-agent LLM-based framework to connect high-level user goals with concrete API endpoints, bridging requirements engineering and implementation. By combining Goal-Oriented Requirements Engineering (GORE) with a Planner/Actor/Observer/Reflector cognitive architecture, SEAL aims to decompose goals into sub-goals and map them to existing APIs via Swagger/OpenAPI documentation, enabling automated or guided API usage. An initial inspirational pilot using CatWatch demonstrates partial success in mapping low-level goals to API calls and highlights non-functional goals that require self-critique and human guidance. The work underscores the potential of semi-autonomous, multi-agent systems to augment software engineering while acknowledging current limitations and outlining directions for empirical evaluation and architecture refinement to reach scalable, end-to-end automation. The approach has practical implications for requirements tracing, API design feedback, and automated code generation within complex software development tasks.

Abstract

Large Language Models (LLMs) are becoming key in automating and assisting various software development tasks, including text-based tasks in requirements engineering but also in coding. Typically, these models are used to automate small portions of existing tasks, but we present a broader vision to span multiple steps from requirements engineering to implementation using existing libraries. This approach, which we call Semantic API Alignment (SEAL), aims to bridge the gap between a user's high-level goals and the specific functions of one or more APIs. In this position paper, we propose a system architecture where a set of LLM-powered ``agents'' match such high-level objectives with appropriate API calls. This system could facilitate automated programming by finding matching links or, alternatively, explaining mismatches to guide manual intervention or further development. As an initial pilot, our paper demonstrates this concept by applying LLMs to Goal-Oriented Requirements Engineering (GORE), via sub-goal analysis, for aligning with REST API specifications, specifically through a case study involving a GitHub statistics API. We discuss the potential of our approach to enhance complex tasks in software development and requirements engineering and outline future directions for research.

Figures (2)

• Figure 1: Main components of the conceptual framework.
• Figure 2: The conceptualized alignment of goals into endpoint calls