Guardado en:
Detalles Bibliográficos
Autores principales: Joshi, Ananya, Rudow, Michael
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.02034
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911416403886080
author Joshi, Ananya
Rudow, Michael
author_facet Joshi, Ananya
Rudow, Michael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02034
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Constrained Process Maps for Multi-Agent Generative AI Workflows
Joshi, Ananya
Rudow, Michael
Artificial Intelligence
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.
title Constrained Process Maps for Multi-Agent Generative AI Workflows
topic Artificial Intelligence
url https://arxiv.org/abs/2602.02034