Jul 2026· International Journal of Innovative Science and Research Technology· 0 citations· 55 references
TL;DR
UMA, a Unified Multi-Agent Framework for enterprise AI systems, is introduced, designed to support the complete lifecycle of agentic systems, including deployment, orchestration, execution, monitoring, and return-on-investment (ROI) realization.
Abstract
The rapid advancement of artificial intelligence is driving a fundamental transformation in enterprise
computing, shifting from traditional software-as-a-service (SaaS) models to agent-as-a-service (AaaS) paradigms powered
by autonomous, goal-driven systems. Although large language models (LLMs) have significantly enhanced reasoning and
content generation capabilities, their effective adoption in enterprise environments requires scalable orchestration, cost
efficiency, and seamless integration with complex workflows. This paper introduces UMA, a Unified Multi-Agent
Framework for enterprise AI systems, designed to support the complete lifecycle of agentic systems, including deployment,
orchestration, execution, monitoring, and return-on-investment (ROI) realization. The proposed framework integrates
multi-agent coordination, tool orchestration, memory management, and adaptive decision-making within a layered
architecture that enables scalable and efficient enterprise operation.
Through an analysis of enterprise use cases and real-world system implementations, it is demonstrated that agentbased systems can autonomously execute complex tasks, reduce human workload, and improve operational efficiency
across business functions. Furthermore, a performance and economic model is presented to quantify the trade-offs
between cost, scalability, and autonomy in enterprise AI deployments. The findings highlight the transformative potential
of UMA in enabling scalable, efficient, and intelligent enterprise systems, positioning agent-as-a-service as a foundational
paradigm for the next generation of enterprise computing.
Cloud-edge computing environments are evolving rapidly, requiring orchestration mechanisms that may automatically construct and manage complex multi-step workflows with little human intervention. We introduce a framework for the agentic AI and how it should be able to orchestrate an autonomous end-to-end workload of cloud-edge enterprise infrastructures in general. The proposed framework relies on large language model (LLM)-driven agents capable of dynamic task decomposition, real-time decision-making, and self-correcting execution pipelines to manage heterogeneous workloads. Through the incorporation of multi-agent coordination protocols, context-aware scheduling algorithms, and feedback-driven optimization loops, the system facilitates seamless task delegation throughout edge nodes and cloud backend systems while managing latency, resource allocation, and compliance constraints. Experimental evaluations show up to percentage improvements in workflow completion rates, resource utilization, and fault tolerance over traditional static-command Rule-based orchestration approaches. Additionally, the framework features explainability modules and audit trails to promote transparency and accountability in autonomous operations. The results provide evidence that agentic AI architectures can serve as a scalable, resilient and intelligent control mechanism for next generation enterprise workflow management across hybrid cloud-edge settings. This has laid a foundation and is to our best of knowledge, the first systematic pioneers work that lays down a roadmap for production-grade autonomous orchestration deployed in analytics and enterprise domains.
Shiza Arshad, Anusha Joodala, A. Agade et al.· 2026 International Conferenc...· 0 citations
This workshop aims to bring together researchers and practitioners to examine how enterprise AI agents can successfully move from prototypes to production, and focuses on three pillars: 1) Agent architectures and systems; 2) Enterprise applications and deployments; 3) Evaluation and governance.
Min Du, Anbang Xu, Jasmine Jaksic et al.· Proceedings of the 32nd ACM...· 0 citations
With the advent of Artificial Intelligence (AI), the world of enterprise automation has radically changed to an AI multi-agent ecosystem with coordination across functional teams and the capacity to make autonomous decisions. Despite this, many companies are still discontinuing the implementation of AI, with partial integration into their processes, weak systems integration, and a lack of a sense of network in some business units. It introduces the concept of the traditional enterprise transforming into an intelligent, autonomous enterprise with the help of AI in logistics, knowledge management, finances, HR, cybersecurity, compliance, customer support, and operational analytics, and also introduces the Multi-Agent Enterprise Framework (MAEF) as the scalable architecture. The proposed architecture has four layers: shared memory, human in the loop, policy-driven control, and orchestration layer, which are necessary for safe, transparent, and trustworthy cooperation between the set of specialized agents. Training is conducted in a highly realistic business environment that includes several departments, numerous workflow requests, and is evaluated and tested against standard automated and single-agent AI systems. Experimental results show that workflow automation and task completion time have been enhanced, cross-department collaboration has been effective, operational efficiency has been achieved, and resources are used optimally; meanwhile, the governance and compliance requirements are met. Agreeing with these conclusions, it seems that enterprise-wide multi-agent systems are a good building block for digital enterprises capable of adapting, scaling, and operating autonomously, on which future intelligent businesses would be able to operate.
Swaroop Suresh Borukar· International Research Journ...· 0 citations
Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot reason about exceptions and monolithic AI assistants degrade when asked to coordinate across functional boundaries. This paper presents Agentic ERP, an expert-system architecture that combines role-aligned large-language-model (LLM) agents with a risk-tiered human-in-the-loop harness and a graph-based orchestrator to execute end-to-end business workflows on a production ERP backend. First, autonomous ERP operation is formulated as a constrained sequential-decision problem over a structured enterprise state, with a decomposition argument linking role-aligned agents to a measurable reduction in per-step tool-selection complexity. Second, a graph-based Planner--Executor--Reflector--Responder orchestration decouples generation from evaluation through externalised grading criteria and sprint contracts, packaging recent harness-engineering principles as inspectable expert-system artefacts. Third, the system is evaluated at three levels: a scenario-based task suite, a comprehensive comparison of six orchestration paradigms on cross-functional crisis tasks, and a 365-day agent-in-the-loop simulation against rule-based RPA and no-intervention baselines. Across these levels the proposed multi-agent method is significantly better than the baseline, and the system sustains a simulated year of operation with zero stockouts while the rule-based baseline accumulates hundreds under the same demand stream. The work shows that role-aligned LLM agents under human oversight can move an ERP system from passively recording transactions to actively executing operational decisions, and it provides a reference architecture and an evaluation protocol for autonomous enterprise resource planning.
Zhihao Liu, Tianyu Wang, X. Wang et al.· 0 citations
The rapid diffusion of data‑driven automation and agentic AI systems is reshaping the foundations of work, decision‑making, and human–technology interaction. As organizations move toward Society 5.0— Japan’s vision for a human-centered “super smart” society in which cyber-physical intelligence augments human capability across economic and social systems—there is an urgent need for operational architectures that are not only technologically capable but also fundamentally human‑centric. This paper presents an applied model using Intelligent Operations framework that integrates agentic AI, enterprise data fabric, human‑in‑the‑loop governance, and secure multi‑system orchestration, and enterprise digital twins that simulate processes and operational states for context-aware decision support. The result is an adaptive socio‑technical system that enhances human decision‑making rather than replacing it, while simultaneously enabling automation at operational scale.The research builds on fieldwork across finance, supply chain, HR, and complex asset‑intensive environments, where organizational processes are distributed across heterogeneous platforms such as ERP, HCM, workflow systems, enterprise data lakes, RPA tools, and emerging AI orchestration layers. Traditional human‑computer interaction models are insufficient in these environments because workers face fragmented data landscapes, inconsistent process execution, and increasing cognitive load. The proposed Intelligent Operations framework addresses these pain points by introducing an orchestration layer that harmonizes data, interprets context (including real-time insights from digital twin models), and deploys agentic AI workers capable of completing multi‑step tasks across systems.A key contribution of this work is the definition of agentic AI in enterprise socio‑technical ecosystems—AI agents equipped not only with language models and planning capability but also with secure access to enterprise systems through structured patterns such as passthrough APIs, workflow orchestration, Model Context Protocol (MCP), and agent‑to‑agent (A2A) collaboration. Rather than relying on brittle rule‑based workflows, the agents dynamically interpret goals, assess context, and plan actionable sequences while maintaining traceability, decision lineage, and auditability. This supports a new form of “digital labor” that works alongside human employees to augment cognitive, administrative, and analytical tasks. However, the framework insists on human‑in‑the‑loop governance, recognizing that human oversight remains essential for ethical, safe, and responsible AI deployment. The DMO acts as a security and compliance boundary—enforcing identity controls, audit trails, approval checkpoints, policy enforcement, and anomaly detection throughout the agentic automation lifecycle. This hybrid model ensures that automation amplifies human capability without bypassing institutional safeguards or creating new forms of risk.The paper also discusses the human‑centric business implications: reduced cognitive load for knowledge workers, increased transparency of decision processes, improvements in cross‑functional collaboration, and the redefinition of roles as humans transition from transactional executors to supervisors, interpreters, and strategic actors. Proposed framework becomes the backbone for Society 5.0 organizational design—linking people, processes, data, and intelligent systems through a unified operational fabric.This research demonstrates that when designed with ergonomics, human values, and socio‑technical principles at the center, agentic AI become powerful enablers of human‑centric, resilient, and adaptive enterprises.
Elizabeth Koumpan, Laurentiu Gabriel Ghergu, Łukasz Strack et al.· AHFE International· 0 citations
Large Language Models (LLMs) have spurred the development of agentic artificial intelligence systems that can reason autonomously, plan, use tools, integrate memory, and carry out multi-step tasks. Unlike conventional prompt-response systems, LLM-based agents extend generative models to goal-oriented architectures that can decompose complex objectives, interact with external environments, and coordinate actions in iterative workflows. The survey systematically reviews LLM-based agent frameworks, multi-agent collaboration architectures, internal communication mechanisms, emerging cross-system interoperability protocols, and open research challenges. The review uses a PRISMA-based methodology, including literature from 2020 to March 2026, with particular focus on prominent frameworks such as LangChain, AutoGPT, AutoGen, MetaGPT, CAMEL, ChatDev, and CrewAI. The survey discusses the transition from modular chain-oriented to stateful graph-oriented and autonomous execution models and presents a systematic taxonomy of multi-agent collaboration architectures, including hierarchical, peer-to-peer, and role-based models. It also reviews the main internal communication mechanisms used to facilitate coordination and information sharing between LLM-based agents and distinguishes them from emerging interoperability protocols designed to support interaction across heterogeneous agents, tools, services, and frameworks. The analysis indicates that the promise of LLM-based agents for scalable automation, collaborative reasoning, and complex workflow execution comes with significant challenges in long-horizon reliability, evaluation standardization, communication security, cost-efficient orchestration, governance, and the interpretability of emergent multi-agent behavior. The survey covers architectural evolution, collaboration patterns, communication mechanisms, framework-level characteristics, and open research challenges. This provides a structured foundation for future research on reliable and trustworthy agentic artificial intelligence systems.
Unknown authors· Journal of Smart Algorithms...· 0 citations