Agentic design patterns: A system-theoretic framework

Simple item page
dc.contributor.authorDao, Dungen
dc.contributor.authorLe, Quy Minhen
dc.contributor.authorLam, Hoang Thanhen
dc.contributor.authorLe, Duc-Trongen
dc.contributor.authorPham, Quoc-Vieten
dc.contributor.authorO'Sullivan, Barryen
dc.contributor.authorNguyen, Hoang D.en
dc.contributor.funderResearch Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.date.accessioned2026-01-06T11:09:09Z
dc.date.available2026-01-06T11:09:09Z
dc.date.issued2025en
dc.description.abstractWith the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle applications. Existing efforts to characterise agentic design patterns often lack a rigorous systems-theoretic foundation, resulting in high-level or convenience-based taxonomies that are difficult to implement. This paper addresses this gap by introducing a principled methodology for engineering robust AI agents. We propose two primary contributions: first, a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems: Reasoning & World Model, Perception & Grounding, Action Execution, Learning & Adaptation, and Inter-Agent Communication. Second, derived from this architecture and directly mapped to a comprehensive taxonomy of agentic challenges, we present a collection of 12 agentic design patterns. These patterns — categorised as Foundational, Cognitive & Decisional, Execution & Interaction, and Adaptive & Learning — offer reusable, structural solutions to recurring problems in agent design. The utility of the framework is demonstrated by a case study on the ReAct framework, showing how the proposed patterns can rectify systemic architectural deficiencies. This work provides a foundational language and a structured methodology to standardise agentic design communication among researchers and engineers, leading to more modular, understandable, and reliable autonomous systems.en
dc.description.sponsorshipResearch Ireland (12-RC-2289-P2)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationDao, D., Le, Q. M., Lam, H. T., Le, D.-T., Pham, Q.-V., O'Sullivan, B. and Nguyen, H. D. (2025) 'Agentic design patterns: A system-theoretic framework', NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW), San Diego, California, United States, 6 December 2025.en
dc.identifier.endpage13en
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/18366
dc.language.isoenen
dc.relation.ispartofThirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA, 2-7 December 2025en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/Centres for Research Training (CRT) Programme/18/CRT/6223/IE/SFI Centre for Research Training in Artificial Intelligence/en
dc.rights© 2025, the Authors. For the purpose of Open Access, the author has applied a CC BY-NC 4.0 public copyright licence to any Author Accepted Manuscript version arising from this submissionen
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.statusNot peer revieweden
dc.subjectFoundation modelen
dc.subjectAgentic AIen
dc.titleAgentic design patterns: A system-theoretic frameworken
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2025_NeurIPS_Agentic_Design_Pattern.pdf
Size:
1.22 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items
ADVANCE CRT - Conference Items
Insight Centre for Data Analytics - Conference Items