Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines
For practitioners maintaining legacy LLM pipelines, this provides a practical migration path to adaptive workflows, though the solution is incremental and domain-specific.
The paper addresses the problem of static expert LLM workflows that cannot adapt based on feedback, proposing a reversible Strangler-Fig migration path and a three-tier convertibility taxonomy (A/B/C) to refactor legacy workflows into composable, typed, and auditable stages. The taxonomy diagnoses workflow readiness and routes execution accordingly.
While expert-validated "LLM + script" workflows deliver significant value, they remain static: they encode hard-won domain knowledge yet fail to adapt execution based on feedback. Existing agent research predominantly targets greenfield agents and synthetic benchmarks, leaving the migration of active legacy workflows unresolved. To bridge this gap, we present a reversible, Strangler-Fig migration path that refactors legacy workflows into composable, typed, and auditable stages. Central to this framework is a three-tier convertibility taxonomy (A/B/C), implemented as a routing stage within the system harness, which diagnoses a workflow's readiness and routes it accordingly.