AutoRestTest at the SBFT 2026 Tool Competition
For black-box REST API testing, AutoRestTest provides a top-performing tool that significantly outperforms competitors in a standardized competition.
AutoRestTest, combining a Semantic Property Dependency Graph, multi-agent reinforcement learning, and LLMs, ranked first in all three categories (fault detection, efficiency, effectiveness) at SBFT 2026, averaging 67.09 unique server errors and 17.27 successful operations per API under one hour.
Large input spaces and complex inter-operation dependencies make black-box REST API testing challenging. AutoRestTest combines a Semantic Property Dependency Graph, multi-agent reinforcement learning, and large language models to intelligently explore large API input spaces. In the SBFT 2026 REST League, AutoRestTest ranked first in all three evaluation categories -- fault detection, overall efficiency, and overall effectiveness -- on 11 APIs (317 operations, approximately 29 per API), averaging 67.09 unique server errors and 17.27 successfully processed operations per API under a one-hour testing budget.