Constrained Process Maps for Multi-Agent Generative AI Workflows

TL;DR

This paper introduces a formal multi-agent framework for AI workflows, enabling better uncertainty management and coordination, demonstrated through a safety evaluation case study with significant accuracy and efficiency improvements.

Contribution

It presents a novel multi-agent system formalized as a finite-horizon MDP with uncertainty quantification, enhancing AI workflow transparency and performance.

Findings

Up to 19% accuracy improvement over single-agent baseline

Up to 85x reduction in human review requirements

Reduced processing time in some configurations

Abstract

Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a single agent, making it difficult to observe or compare how models handle uncertainty and coordination across interconnected decision stages and with human oversight. We introduce a multi-agent system formalized as a finite-horizon Markov Decision Process (MDP) with a directed acyclic structure. Each agent corresponds to a specific role or decision stage (e.g., content, business, or legal review in a compliance workflow), with predefined transitions representing task escalation or completion. Epistemic uncertainty is quantified at the agent level using Monte Carlo estimation, while system-level uncertainty is captured by the MDP's termination in either an automated labeled state or a human-review state. We illustrate the approach through a case study in AI safety evaluation for self-harm detection, implemented as a multi-agent compliance system. Results demonstrate improvements over a single-agent baseline, including up to a 19\% increase in accuracy, up to an 85x reduction in required human review, and, in some configurations, reduced processing time.