{"ID":5551894,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T01:45:22.703757252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00345","arxiv_id":"2607.00345","title":"Registry-Governed Agent Lifecycle:Completing EDDOps with Evaluation-DrivenRegistration, Promotion, and Retirement on AWS AgentCore","abstract":"Enterprise adoption of LLM agents requires model selection methods that balance quality, reliability, safety, latency, and cost. Evaluation-Driven Development and Operations (EDDOps) positions evaluation as a continuous governing function across the agent lifecycle rather than a terminal checkpoint. This paper presents a practitioner-oriented instantiation of EDDOps on AWS Bedrock AgentCore and proposes a cost-to-performance framework for selecting foundation models in enterprise agent architectures. We make three contributions: a conceptual synthesis explaining why traditional TDD/BDD methods are insufficient for non-deterministic LLM agents; an architectural mapping of the EDDOps reference architecture onto AgentCore Runtime, Evaluations, Agent Registry, and CloudWatch observability; and an empirical cost-to-performance decision framework validated through a proof-of-concept comparing three foundation models across two deployment paths. Using trace data from 30 single-turn invocations across six agents, 9 multi-turn evaluations, and registry-integrated governance, we show how evaluation evidence can convert model selection from a benchmark-ranking exercise into a governed economic decision. The results suggest that managed agent platforms can support EDDOps when they provide trace-native observability, pluggable evaluator frameworks, and governed registry-based discovery.","short_abstract":"Enterprise adoption of LLM agents requires model selection methods that balance quality, reliability, safety, latency, and cost. Evaluation-Driven Development and Operations (EDDOps) positions evaluation as a continuous governing function across the agent lifecycle rather than a terminal checkpoint. This paper presents...","url_abs":"https://arxiv.org/abs/2607.00345","url_pdf":"https://arxiv.org/pdf/2607.00345v1","authors":"[\"Richard Kang\",\"Vincent Wang\"]","published":"2026-07-01T02:41:08Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false}