arXiv AI By Liming Zhu, Qinghua Lu, Ming Ding

Understanding-First AI Engineering: Purposes, Reference Architecture, and Architectural Patterns for Human Understanding

Read the original on arXiv AI →

The paper proposes an "understanding-first AI engineering" approach that prioritises human understanding as a core design principle for AI systems. It categorises purposes of understanding into reflective agency, effective action, collective governance, and epistemic value, and presents a reference architecture linking production, verification, use, and learning through shared records. Five architectural patterns—parallel learning, explanatory models, goal exploration, audience‑specific views, and distributed expertise—are suggested to guide design choices, with scenario analyses illustrating their application and limitations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Sep 28

What Will Remain Human in Software Architecture? A Focus Group Report

The report examines how software architects view the growing use of AI development agents in their field. A focus group of 22 industry and academic participants discussed current practices, trust, validation, governance, and educational implications, concluding that decision‑making, accountability, and guardrail authoring remain human responsibilities. They introduced the concept of harness engineering—building systems that govern AI‑assisted creation—and identified criticality and cognitive debt as key factors for calibrating human oversight.

By Uwe van Heesch, Olaf Zimmermann, Christian Kohls
arXiv AI
Sep 28

Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge

The paper explores how Artificial Intelligence can enhance cooperative engineering workflows, focusing on the European Rover Challenge where student teams design complex rover systems under tight deadlines. A 40‑question survey of 14 teams revealed common bottlenecks such as poor documentation, unclear requirements, fragmented communication, informal task monitoring, and significant integration rework. Based on these findings, the authors propose requirements for AI‑augmented workflows and outline an assistant system architecture that integrates user interfaces, credential management, service selection, specialized AI services, and external engineering tools to support task clarification, requirement compliance, communication summarization, integration risk detection, and continuous knowledge capture.

By Ahmed R. Sadik, Frank Joublin, Mariusz Bujny, Antonello Ceravola, Joan Smith
arXiv AI
Jun 10

Human-AI Coordination Zones: A Framework for Designing Human-in-the-Loop Experiences with Agentic AI

arXiv:2606. 09848v1 Announce Type: cross Abstract: As generative and agentic AI becomes embedded in everyday products, practitioners face a persistent challenge: how to design human-AI coordination -- the ongoing mutual adjustment between users and AI systems as mediate through interfaces-that supports usability, trust, and safety.

By James Pierce, Vaiva Kalnikait\.e, Siddharth Gupta, Brian Granger
arXiv AI
3d ago

Open Challenges and Opportunities in Human-Agent Systems

The paper "Open Challenges and Opportunities in Human-Agent Systems" discusses how agentic AI systems increasingly perform extended tasks on behalf of people, making human‑agent interaction essential. It reviews computational approaches—such as Theory of Mind, belief‑desire‑intention models, goal and plan recognition, observer‑aware planning, and cooperative inverse reinforcement learning—that help agents understand human perspectives, coordinate complementary capabilities, and maintain productive relationships in socio‑technical environments. The authors argue that progress requires treating human interaction as an ongoing decision problem shaped by uncertainty, interdependence, and potentially conflicting objectives.

By Reuth Mirsky, Sarath Sreedharan, Nitay Alon, Stefan Sarkadi, Munindar P. Singh, Liz Sonenberg, Peter Stone, Silvia Tulli, Stylianos Loukas Vasileiou, Shlomo Zilberstein