Agentic LLMs for REST API Test Amplification: A Comparative Study Across Cloud Applications

2025-10-31

AI Summary

REST API test case generation for cloud-native systems remains heavily manual, suffers from low coverage—particularly of edge-case behaviors—and lacks scalability. Method: This paper proposes a large language model (LLM)-based framework for test amplification, supporting both single-agent and multi-agent collaborative testing, integrated with a semantic validity verification mechanism to automate and diversify endpoint and parameter test generation. Contribution/Results: We conduct the first systematic cross-application evaluation of agent configurations across heterogeneous cloud applications, quantifying trade-offs among computational overhead, execution time, and energy consumption. Experiments demonstrate significant improvements in endpoint and parameter coverage, successful identification of real-world defects, and validate the feasibility and practicality of LLM agents for efficient, sustainable automated testing in complex cloud environments.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Representational State Transfer (REST) APIs are a cornerstone of modern cloud native systems. Ensuring their reliability demands automated test suites that exercise diverse and boundary level behaviors. Nevertheless, designing such test cases remains a challenging and resource intensive endeavor. This study extends prior work on Large Language Model (LLM) based test amplification by evaluating single agent and multi agent configurations across four additional cloud applications. The amplified test suites maintain semantic validity with minimal human intervention. The results demonstrate that agentic LLM systems can effectively generalize across heterogeneous API architectures, increasing endpoint and parameter coverage while revealing defects. Moreover, a detailed analysis of computational cost, runtime, and energy consumption highlights trade-offs between accuracy, scalability, and efficiency. These findings underscore the potential of LLM driven test amplification to advance the automation and sustainability of REST API testing in complex cloud environments.

Problem

• Evaluating agentic LLMs for REST API test amplification across cloud applications
• Increasing endpoint coverage and defect detection in automated API testing
• Analyzing trade-offs between accuracy, scalability and computational efficiency

Innovation

• Agentic LLMs amplify REST API tests
• Multi-agent systems generalize across API architectures
• Automated test suites increase coverage with minimal intervention