# Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines

arXiv: https://arxiv.org/abs/2606.24598 · HTML: https://mlsanity.com/paper/2606.24598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions](https://mlsanity.com/paper/2601.06112/) (2026)
- [Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents](https://mlsanity.com/paper/2603.20953/) (2026)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [Bypassing Prompt Guards in Production with Controlled-Release Prompting](https://mlsanity.com/paper/2510.01529/) (2025)
- [The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search](https://mlsanity.com/paper/2512.01353/) (2025)
- [Code Reborn AI-Driven Legacy Systems Modernization from COBOL to Java](https://mlsanity.com/paper/2504.11335/) (2025)
- [Trustworthy Agentic AI Requires Deterministic Architectural Boundaries](https://mlsanity.com/paper/2602.09947/) (2026)
- [Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts](https://mlsanity.com/paper/2605.12105/) (2026)
- [Contemporary Software Modernization: Perspectives and Challenges to Deal with Legacy Systems](https://mlsanity.com/paper/2407.04017/) (2024)
- [Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI](https://mlsanity.com/paper/2602.10481/) (2026)
- [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://mlsanity.com/paper/2604.23049/) (2026)

## Abstract (arXiv)

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.