Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO

Source

arXiv

arxiv.org/abs/2606.27188v1

Read the source

Source

Plain-Language Brief

Researchers introduce a new mechanism called the 'process harness' to upgrade legacy workflow systems into Agentic Business Process Management (Agentic BPM) without replacing the existing engine. The process harness includes a policy-guided agent layer that interacts with the workflow engine at designated control points, offering reasoning, adaptation, and oversight while the engine maintains structural authority over the process. The researchers define the Task-Decision-Flow (TDF) model to explain this system, detailing its data schema and execution semantics. TDF separates LLM reasoning into three policy-guided agent types: TaskAgent, DecisionAgent, and FlowAgent. Each agent operates within a policy derived from the process FRAME. The research group then presents CUGA FLO as an implementation of this model, demonstrating it on a loan approval workflow that uses all three agent types and hook-driven regulatory override.

What the Document Says

  • The process harness is a new mechanism for upgrading legacy workflow systems to Agentic Business Process Management (Agentic BPM) without replacing the underlying engine.
  • The process harness includes a policy-guided agent layer that interacts with the workflow engine at designated control points.
  • The system offers reasoning, adaptation, and oversight while the engine retains structural authority over the process.
  • The researchers define the Task-Decision-Flow (TDF) model to explain this system.
  • TDF separates LLM reasoning into three policy-guided agent types: TaskAgent, DecisionAgent, and FlowAgent.
  • Each agent operates within a policy derived from the process FRAME.
  • CUGA FLO is presented as an implementation of the TDF model.

Key Concepts Mentioned

  • process harness
  • Legacy Workflows
  • Agentic Business Process Management (Agentic BPM)
  • Task-Decision-Flow (TDF) model
  • policy-governed agent types
  • CUGA FLO

Claims Made by the Document

  • The process harness can upgrade legacy workflow systems to Agentic BPM without replacing the underlying engine.
  • The system offers reasoning, adaptation, and oversight while retaining structural authority.

Evidence Used

  • We introduce the process harness...
  • A process harness places a policy-governed agentic layer around a deterministic workflow engine...
  • To define the process harness rigorously, we develop the Task-Decision-Flow (TDF) model...
  • We then present CUGA FLO as the design and implementation realization of the TDF model...

Methods / Approach

  • The development of the Task-Decision-Flow (TDF) model to define the process harness.
  • The presentation of CUGA FLO as an implementation of the TDF model.

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

Not stated in source

Open Questions

  • How effective is the process harness in improving the performance and adaptability of legacy workflow systems?
  • What are the potential challenges or trade-offs in implementing the TDF model and CUGA FLO in real-world scenarios?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The research focuses on introducing a new mechanism for upgrading legacy workflow systems. However, it does not provide information on the performance improvements or practical challenges that may arise when implementing this approach.

Raw Abstract / Excerpt

We introduce the process harness, a new mechanism for uplifting legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the underlying workflow engine. A process harness places a policy-governed agentic layer around a deterministic workflow engine, intercepting designated control points to contribute reasoning, adaptation, and oversight while the engine retains structural authority over the process. To define the process harness rigorously, we develop the Task-Decision-Flow (TDF) model, specifying both its data schema and its execution semantics. TDF decomposes LLM reasoning across three policy-governed agent types: a TaskAgent for knowledge-intensive task execution, a DecisionAgent for per-case gateway routing, and a FlowAgent that governs runtime flow adaptation through a principled hook mechanism. Each agent reasons within an explicit policy drawn from the process FRAME, the aggregate policy set governing all LLM calls in the system. We then present CUGA FLO as the design and implementation realization of the TDF model, and demonstrate it on a loan approval workflow that exercises all three agent types and hook-driven regulatory override. The process harness uniquely reconciles imperative requirements, realized through deterministic workflow execution that enforces structural compliance, with normative requirements, realized through policy-framed agentic autonomy invoked at designated control points wherever the process demands it.