Making Sense of AI Agents Hype: Adoption, Architectures, and Takeaways from Practitioners

Ruoyu Su; Matteo Esposito; Roberta Capuano; Rafiullah Omar; June Sallou; Henry Muccini; Davide Taibi

cs.SEMar 31, 2026

Making Sense of AI Agents Hype: Adoption, Architectures, and Takeaways from Practitioners

Authors: Ruoyu Su, Matteo Esposito, Roberta Capuano, Rafiullah Omar, June Sallou, Henry Muccini, Davide Taibi

Organizations: University of Oulu, Oulu, Finland · University of L’Aquila, L’Aquila, Italy · Wageningen University, Wageningen, The Netherlands · University of Southern Denmark, Vejle, Denmark

Abstract

To support practitioners in understanding how agentic systems are designed in real-world industrial practice, we present a review of practitioner conference talks on AI agents. We analyzed 138 recorded talks to examine how companies adopt agent-based architectures (Objective 1), identify recurring architectural strategies and patterns (Objective 2), and analyze application domains and technologies used to implement and operate LLM-driven agentic systems (Objective 3).

Figures & tables

Panel of Figure 1 — Figure 1: Timeline of industrial adoption phases for AI agent-based architectures.

Panel of Figure 2 — Figure 2: Compact overview of key architectural strategies and structural patterns identified for Objective 2.

Explore similar work

Agents in the Wild: Where Research Meets Deployment
Jul 21, 2026Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz +3AI Agent Reliability Multi-Agent LLM Systems
Georgetown University · Washington, D.C., USA · Salesforce +7
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
Oct 8, 2026Irene WeberLLM Agents LLM Agent Orchestration
University of Applied Sciences Kempten, Germany
Architecture Without Architects: How AI Coding Agents Shape Software Architecture
Apr 5, 2026Phongsakon Mark Konrad, Tim Lukas Adam, Riccardo Terrenzi +1AI Coding Agents Software Engineering
Centre for Industrial Software, University of Southern Denmark, Alsion 2, Sønderborg, 6400, Denmark

Jul 21, 2026J/K move · Enter open · S save

Agents in the Wild: Where Research Meets Deployment

Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz, Enrico Santus+2

Georgetown University · Washington, D.C., USA · Salesforce+7

AI Agent Reliability Multi-Agent LLM Systems LLM Agent Evaluation LLM Agents LLM Agent Safety LLM Agent Reliability

Open paper AskPDF arXiv

Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance. While academic work has emphasized benchmarks and algorithmic innovation, deployment raises new challenges around robustness, safety, and reliability. This tutorial brings together researchers and practitioners to explore advances in reasoning and planning, multi agent coordination, and evaluation, highlighting open challenges arising from deployment experience. Through applied case studies in pharmaceutical discovery and financial systems, we analyze common design patterns that make agentic systems successful, and discuss practical mitigation strategies for failure modes, such as verification pipelines, fallback mechanisms, and human in the loop supervision. Attendees will gain a comprehensive view of the field along with concrete design patterns, evaluation checklists, and templates for safe and reliable deployment across industries.

Abstract

Explore similar work

Agents in the Wild: Where Research Meets Deployment

Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System

Architecture Without Architects: How AI Coding Agents Shape Software Architecture