{"ID":5551600,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T15:13:22.648032999Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01063","arxiv_id":"2607.01063","title":"AutoRestTest at the SBFT 2026 Tool Competition","abstract":"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.","short_abstract":"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 r...","url_abs":"https://arxiv.org/abs/2607.01063","url_pdf":"https://arxiv.org/pdf/2607.01063v1","authors":"[\"Tyler Stennett\",\"Myeongsoo Kim\",\"Saurabh Sinha\",\"Alessandro Orso\"]","published":"2026-07-01T15:24:38Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}