mlsanityData to 14 Oct 2026

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

arXiv 2606.24598 ↗First posted 15 Jun 2026cs.SE cs.AI cs.LGcited by 0

Not on the map. Why?

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.

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

24 of 29 references.

References · 24

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  7. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 223
  8. 2025Survey on Evaluation of LLM-based Agentscited by 204
  9. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 195
  10. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 168
  11. 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoningcited by 151
  12. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
12 more
  1. 2024Human-In-the-Loop Software Development Agentscited by 42
  2. 2026ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditionscited by 36
  3. 2026Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agentscited by 13
  4. 2026A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Frameworkcited by 11
  5. 2025Bypassing Prompt Guards in Production with Controlled-Release Promptingcited by 7
  6. 2025The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Searchcited by 7
  7. 2025Code Reborn AI-Driven Legacy Systems Modernization from COBOL to Javacited by 4
  8. 2026Trustworthy Agentic AI Requires Deterministic Architectural Boundariescited by 3
  9. 2026Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contextscited by 3
  10. 2024Contemporary Software Modernization: Perspectives and Challenges to Deal with Legacy Systemscited by 1
  11. 2026Protecting Context and Prompts: Deterministic Security for Non-Deterministic AIcited by 1
  12. 2026A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflowscited by 1

Built on by

Not cited yet.