Co-located with ICSA 2027
AgentArch 2027
International Workshop on Architecting Agentic AI Systems
International Workshop on Architecting Agentic AI Systems
AgentArch addresses a critical gap in current research by positioning agentic AI systems as a new class of software systems that require dedicated architectural principles, patterns, and evaluation methodologies.
The rapid emergence of large language model (LLM)-based agents is transforming artificial intelligence from standalone models into complex, interactive software systems involving AI agents, multi-agent ecosystems, and human-AI collaboration. However, current research remains largely model-centric, with limited attention to the architectural foundations required to design, analyse, and govern such systems.
Recent advances in LLMs have rapidly shifted the focus of AI from standalone models to agentic systems, where LLMs are embedded within iterative reasoning, tool usage, and decision-making loops. These systems can function as autonomous or semi-autonomous agents that plan, invoke tools, and collaborate with humans or other agents in dynamic environments. This paradigm shift has led to the emergence of AI agents, multi-agent ecosystems, and human-AI collaborative systems across domains such as software engineering, healthcare, finance, and digital services.
This shift reflects a transition from model-centric AI to system-centric AI, in which agents function as executable entities with state, behaviour, and interaction capabilities. Agentic systems are no longer merely collections of models, but a new class of software systems that require principled design beyond model-level optimisation. Despite this rapid progress, existing agent frameworks are often constructed in an ad hoc manner, lacking principled abstractions for modularity, coordination, observability, and control.
AgentArch focuses on three interconnected dimensions: (i) the architecture of individual AI agents, including reasoning pipelines, memory, and tool integration; (ii) multi-agent systems, including coordination, communication, and emergent behaviours; and (iii) human-agent collaboration, where agents support or influence human decision-making processes. The workshop emphasises core architectural concerns, including modularity, composability, observability, reliability, and trust.
From an architectural perspective, agentic systems raise new challenges. AI agents can be viewed as modular and composable units, analogous to services in microservice architectures; however, unlike traditional services, they exhibit non-deterministic behaviour, maintain internal reasoning states, and interact with tools through complex feedback loops. Multi-agent systems introduce distributed and decentralised architectures requiring support for coordination protocols and conflict resolution. Human-agent collaboration introduces socio-technical considerations, raising concerns around transparency, traceability, controllability, and bias.
The scope of this workshop aligns well with the ICSA 2027 theme: the enduring role of software architecture in an evolving landscape. By bringing together researchers and practitioners across disciplines, the workshop aims to identify key challenges, develop architectural principles, and establish a research agenda for architecting next-generation AI-driven systems.
The workshop focuses on the architectural foundations of agentic AI systems, covering a broad yet coherent set of topics across three key dimensions. We particularly encourage work that explicitly considers agentic systems from an architectural perspective, including design principles, reusable patterns, system abstractions, and evaluation methodologies.
The primary goal of the AgentArch workshop is to establish a foundation for understanding and designing agentic AI systems from a software architecture perspective.
A highly interactive full-day workshop combining invited keynote talks, paper presentations, and collaborative working sessions. The format emphasises active participation and collaboration, going beyond traditional paper-centric workshops to foster deeper engagement and community building.
| Session | Duration | Description |
|---|---|---|
| Session 1 | 45 min |
Opening and Keynote
Keynote talk from a leading researcher or practitioner highlighting key challenges and emerging trends in architecting agentic AI systems.
|
| Session 2 | 90 min |
Paper Presentations I
Authors of accepted papers present their work, followed by short Q&A sessions to stimulate discussion and cross-fertilisation of ideas.
|
| Session 3 | 60 min |
Thematic Discussion Session
Organised around key themes — architectural patterns for AI agents; coordination and reliability in multi-agent systems; human-agent collaboration and trust. Each theme is introduced by a moderator, followed by open discussion.
|
| Session 4 | — |
Lunch Break
|
| Session 5 | 90 min |
Paper Presentations II
Authors of accepted papers present their work, followed by short Q&A sessions to stimulate discussion and cross-fertilisation of ideas.
|
| Session 6 | 30 min |
Breakout Working Groups
Small groups collaboratively explore specific research questions — identifying key architectural challenges, proposing design principles or solution directions, and outlining open research problems.
|
| Session 7 | 30 min |
Panel Discussion
Each group presents their findings, followed by a panel discussion involving organisers, invited speakers, and participants.
|
| Session 8 | 15 min |
Future Agenda
Synthesis session to summarise key insights and define a research agenda for architecting agentic AI systems.
|
We solicit contributions across two tracks. All submissions must follow the IEEE Computer Society proceedings format. Accepted papers will be included in the ICSA 2027 Companion Proceedings and published in the IEEE Xplore Digital Library.
Novel frameworks, methodologies, or empirical studies presenting original research on the architectural foundations of agentic AI systems.
Position papers, preliminary results, tool demonstrations, or experience reports exploring emerging ideas and open challenges.
Best Paper Award. The workshop includes a Best Paper Award to recognise outstanding contributions and encourage high-quality submissions, particularly from early-career researchers.
All deadlines are Anywhere on Earth (AoE). Dates will be confirmed following acceptance of the workshop proposal.
| Milestone | Date |
|---|---|
| Paper Submission Deadline | To be announced |
| Notification of Acceptance | To be announced |
| Camera-Ready Deadline | To be announced |
| Workshop Date | 2027 (co-located with ICSA 2027) |
Stay tuned — exact dates will be announced shortly. Follow the ICSA 2027 website for conference updates.
Lecturer in the School of Computing Technologies at RMIT University. His research lies
at the intersection of trustworthy artificial intelligence and software systems, with a
focus on causal inference, fairness-aware machine learning, and LLM-based systems. His
recent work investigates reasoning mechanisms, bias mitigation, and human-AI
decision-making. He has published in leading venues such as AAAI, ICLR, ICML, and WWW,
and serves as a program committee member for top-tier conferences including AAAI.
ziqi.xu@rmit.edu.au
Postdoctoral researcher at the Gran Sasso Science Institute. He earned his Ph.D. in
Computer Science and Mathematics from the University of Camerino. His research focuses
on Software Engineering, with a particular interest in software architecture and the
performance of AI-augmented and agentic systems, especially in the context of Federated
Learning. He also works in Business Process Management, contributing to the modelling
and analysis of IoT-Enhanced Business Processes and Digital Process Twins.
ivan.compagnucci@gssi.it
Senior Lecturer in the School of Computing and Information Science, Faculty of Science
and Engineering, Anglia Ruskin University. He has authored over 80 publications in
leading journals and conferences including IEEE TNNLS, TITS, TCSS, and TCE. His
research interests include intelligent systems, optimisation, computational intelligence,
and data-driven applications. He is an Associate Editor of Complex and Intelligent
Systems and Intelligent Systems with Applications, and was listed among
the World's Top 2% Scientists by Stanford University and Elsevier in 2025.
man-fai.leung@aru.ac.uk
Associate Professor in the School of Computer Science and Technology, Dalian University
of Technology. She has published over 60 papers in ACM/IEEE conferences, journals, and
magazines, including IEEE DataCom 2017 Best Paper Award, IEEE CSDE 2020 Best Paper
Award, and ACM/IEEE JCDL 2020 The Vannevar Bush Best Paper Honorable Mention. Her work
has received more than 1,400 citations. She has delivered keynote talks at nine
international conferences and served as Track Chair and PC member at many international
venues. She is a Senior Member of IEEE.
shuo.yu@ieee.org
Professor of Computer Science and the Daniel St. Clair Endowed Chair at Missouri
University of Science and Technology (S&T), where he also served as Chair of the
Computer Science Department during 2013–2017. He previously served at the US National
Science Foundation as a Program Director in the Computer Networks and Systems division
(2008–2011). His research interests include edge computing, mobile and pervasive
computing, distributed intelligence, smart and connected communities, IoT, and applied
graph theory and game theory. He is a Fellow of the IEEE.
sdas@mst.edu
Professor of AI in the School of Computing Technologies, RMIT University. He has served
as Associate/Guest Editor of over 20 journals and as General Chair, PC Chair, or
Workshop Chair of over 30 conferences. He has published over 400 scientific papers with
an h-index of 82 and more than 27,000 citations (Google Scholar). He was recognised as
a Clarivate Highly Cited Researcher (2019) and a ScholarGPS Highly Ranked Scholar
(2024). Awards include Springer Nature Editor of Distinction 2025 and IEEE Vehicular
Technology Society 2020 Best Land Transportation Paper Award. He is Chair of the IEEE
Task Force on Learning for Graphs, and a Fellow of the IEEE.
Website: xia.ai
f.xia@ieee.org