{"ID":3049951,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T15:44:26.945507316Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05037","arxiv_id":"2606.05037","title":"Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery","abstract":"When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery\\_feedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot ($N{=}30$ per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by $+36.7$--$40.0$pp over plain-English diagnoses on Anthropic models (Fisher's exact $p \\le 0.0022$), at $1.8$--$2.2\\times$ better per-success token efficiency. The lift is not significant on gpt-4o-mini ($p{=}0.435$); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipaudit\\_prompt\\_leakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.","short_abstract":"When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery\\_feedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning...","url_abs":"https://arxiv.org/abs/2606.05037","url_pdf":"https://arxiv.org/pdf/2606.05037v1","authors":"[\"Arquimedes Canedo\",\"Grama Chethan\"]","published":"2026-06-03T16:02:11Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":612764,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-04T02:13:16.786527022Z","DeletedAt":null,"paper_id":3049951,"paper_url":"https://arxiv.org/abs/2606.05037","paper_title":"Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery","repo_url":"https://github.com/arquicanedo/self-reflective-apis","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}