{"ID":6138387,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T17:47:58.155493336Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07689","arxiv_id":"2607.07689","title":"Agent Delivery Engineering Predictive Reliability Framework","abstract":"Long-horizon LLM multi-agent systems face reliability risks invisible to infrastructure monitoring. We propose the ADE Predictive Reliability Framework (ADE-PRF), enabling proactive health trajectory prediction from passive degradation detection. ADE-PRF aggregates 20 heterogeneous signals across five layers into a Trust Margin (TM) metric (39.2-point dynamic range). Triple-method parallel prediction enables 8-hour forecasts: the Exponential method achieves MAE=1.228, Direction Accuracy=76.8%, with 99.65% within +/-10-point tolerance. Production validation spans 380,227 predictions and 280,579 validations across six agent profiles over 15 continuous days, plus seven sandbox-controlled experiments. Key findings include detection of \"false prosperity\" -- degradation concealed by normal surface metrics -- and immediate TM coupling with ground-truth states upon ADE plugin integration, with 16/20 factors relying on ADE-collected data. Exponential consistently outperforms Kalman. ADE-PRF provides among the earliest reliability quantification with forward-looking warnings for production LLM agents.","short_abstract":"Long-horizon LLM multi-agent systems face reliability risks invisible to infrastructure monitoring. We propose the ADE Predictive Reliability Framework (ADE-PRF), enabling proactive health trajectory prediction from passive degradation detection. ADE-PRF aggregates 20 heterogeneous signals across five layers into a Tru...","url_abs":"https://arxiv.org/abs/2607.07689","url_pdf":"https://arxiv.org/pdf/2607.07689v1","authors":"[\"Dexing Liu\"]","published":"2026-07-08T17:49:08Z","proceeding":"cs.MA","tasks":"[\"cs.MA\"]","methods":"[\"Large Language Model\"]","has_code":false}