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

A comprehensive review of 138 practitioner talks to understand how agentic systems are designed in industrial practice, focusing on architectures, strategies, and implementation technologies.

Computer Science > Software Engineering

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

View PDF HTML (experimental)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).

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models

SMAC-Talk is a natural language extension of the StarCraft Multi-Agent Challenge (SMAC), designed to evaluate how LLM agents communicate, coordinate, and build trust. This open benchmark opens new avenues for researching multi-agent cooperation and handling deceptive communication.

agentic-systems

Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-Enabled Research

A new study introduces PEEL, a semiotic framework designed to detect systematic distortions in AI-generated research content, helping researchers maintain epistemic accountability when using large language models.

agentic-systems

Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal

A new study argues that forcing consensus in multi-agent AI systems is insufficient for value-laden tasks. Instead, analyzing disagreements in reasoning traces can serve as a valuable knowledge-representation signal to optimize AI decision-making.

EXPLORE TOPICS