Enhancing Holonic Architecture with Natural Language Processing for

System of Systems

Muhammad Ashfaq

1 a

, Ahmed R. Sadik

2 b

, Tommi Mikkonen

1 c

Muhammad Waseem

1 d

and Niko M

akitalo

1 e

University of Jyv

askyl

a, Jyv

askyl

a, Finland

Honda Research Institute Europe, Germany

ﬁ

Keywords:

System of Systems, Holon Communication, Holonic Architecture, Natural Language Processing,

Conversational Generative Intelligence, Interoperability, Human-System Interaction.

Abstract:

The ever-growing complexity and dynamic nature of modern System of Systems (SoS) necessitate efﬁcient

communication mechanisms to ensure interoperability and collaborative functioning among constituent sys-

tems (CS), referred to as holons in the holonic architecture of SoS. This paper proposes a novel approach to

enhance humand-to-holon and holon-to-holon communication within the holonic architecture through the in-

tegration of Natural Language Processing (NLP) techniques. Our proposed framework utilizes advancements

in NLP, speciﬁcally Large Language Models (LLMs), enabling holons to understand and act on natural lan-

guage instructions. This enables more intuitive holon-to-holon and human-to-holon interactions, leading to

better coordination among diverse systems. The framework’s practical application is demonstrated through an

Unmanned Vehicle Fleet (UVF) case study, showcasing its potential in enhancing communication and coordi-

nation in complex SoS. Additionally, we propose evaluation strategies to assess the efﬁciency and effectiveness

of this framework, and identify areas for improvement. This work sets the stage for future exploration and pro-

totype implementation, paving the way for further advancements in SoS communication and collaboration.

1 INTRODUCTION

A System of System (SoS) is a collection of sys-

tems functioning together to achieve a common

goal (Nielsen et al., 2015). These SoSs are comprised

of multiple Constituent Systems (CS), each func-

tioning independently with its management structure.

CSs within an SoS can be geographically dispersed,

further highlighting the need for effective communi-

cation and coordination. When integrated, the overall

SoS capabilities are far more than that of the individ-

ual CSs forming the SoS. Moreover, an SoS should

support evolutionary development allowing CSs to

join or leave the SoS at runtime to meet the desired

needs. SoS ﬁnds numerous applications in real-life

domains, including energy grids, air trafﬁc manage-

ment, defense, and robotics swarms (Jamshidi, 2008).

https://orcid.org/0000-0003-1870-7680

https://orcid.org/0000-0001-8291-2211

https://orcid.org/0000-0002-8540-9918

https://orcid.org/0000-0001-7488-2577

https://orcid.org/0000-0002-7994-3700

Managing the complexity of SoS is a major chal-

lenge. Traditional approaches often struggle due

to the inherent autonomy and heterogeneous na-

ture of CSs. Holonic architectures (Blair et al.,

2015) offer a promising solution by decomposing

the SoS into smaller, self-governing entities called

holons (Koestler, 1968). This duality facilitates a re-

cursive system architecture, allowing for self-reliance

alongside cooperation with other holons forming

a holarchy—a hierarchy of holons operating au-

tonomously yet in coordination to achieve common

objectives. The holonic approach aligns with key SoS

architectural principles, such as interoperability, scal-

ability, and adaptability. These principles motivate

researchers to represent the CS of SoS as ‘holons’.

This representation enables functionalities such as CS

discovery and dynamic SoS composition (Elhabbash

et al., 2024).

While the holonic architecture offers a promising

approach for SoS engineering, it can face substan-

tial interoperability challenges. The heterogeneous

CSs, or holons, often adhere to distinct data for-

mats, communication protocols, and interaction pat-

Ashfaq, M., Sadik, A., Mikkonen, T., Waseem, M. and Mäkitalo, N.

Enhancing Holonic Architecture with Natural Language Processing for System of Systems.

DOI: 10.5220/0012787300003753

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 19th International Conference on Software Technologies (ICSOFT 2024), pages 427-433

ISBN: 978-989-758-706-1; ISSN: 2184-2833

427

terns. This diversity creates interoperability hurdles,

hindering seamless information sharing, command in-

terpretation, and task collaboration requiring special-

ized knowledge for SoS understanding and imple-

mentation. Moreover, the dynamic nature of SoS,

where CSs can join or leave, necessitates adaptive

and ﬂexible communication mechanisms to handle

evolving SoS compositions. Finally, while in oper-

ation, SoS should have the capability to interact with

humans, necessitating communication to expand to-

wards a form that is immediately understood by hu-

mans.

Empowering holons with Natural Language Pro-

cessing (NLP) capabilities presents a transformative

approach to overcoming the aforementioned commu-

nication hurdles. Such capabilities can enable holons

to interpret and respond to natural language instruc-

tions, thereby simplifying the interaction between

holons and humans and reducing the reliance on in-

ternal system knowledge. Furthermore, this approach

facilitates holon-to-holon communication by encod-

ing and decoding machine-executable commands into

natural language. Thus, the NLP layer acts as a

communication layer among humans and holons, ag-

nostic to underlying CS heterogeneity and protocols,

thereby enhancing overall collaboration and adapt-

ability in SoS.

Recent research explores integrating NLP tech-

nologies, especially Large Language Models (LLMs),

into robots (Koubaa, 2023), leading to improved

human-robot collaboration. However, these studies

do not incorporate multi-robot functionality, which is

essential for robot-to-robot communication. Further-

more, their scope is limited to robotics rather than to

SoS and holonic architecture.

In this paper, we propose extending the holonic ar-

chitecture by integrating the NLP capabilities directly

into the holons. We present a conceptual framework

for NLP-enhanced SoS, enabling natural language in-

teraction and decision-making. Through the utiliza-

tion of advanced NLP technologies, such as LLMs,

our approach facilitates seamless communication and

collaboration within SoS. The framework’s practical

application is demonstrated through an Unmanned

Vehicle Fleet (UVF) case study. To the best of our

knowledge, this is the ﬁrst work of its kind to explore

NLP-enhanced holonic architectures within the SoS

domain.

The remainder of this paper is organized as fol-

lows. Section 2 provides background information on

NLP and holonic architecture. Section 3 reviews the

state of the art in this topic. Section 4 details the pro-

posed conceptual framework incorporating NLP into

the holonic architecture. Section 5 demonstrates the

application of the framework to the UVF case study.

Section 6 presents ideas for evaluating the framework.

Section 7 discusses our ﬁndings and their implica-

tions. Finally, Section 8 concludes the paper by draw-

ing ﬁnal conclusions and outlining potential avenues

for future work.

2 BACKGROUND

2.1 Natural Language Processing

Natural Language Processing (NLP) has become a

cornerstone of artiﬁcial intelligence, facilitating com-

munication between humans and computers (Khu-

rana et al., 2023). It encompasses various techniques

for enabling computers to understand, interpret, and

generate human language. Among these techniques,

Large Language Models (LLMs) have revolutionized

the capabilities of machines in processing and gener-

ating human-like text. These LLMs, such as BERT

(Bidirectional Encoder Representations from Trans-

formers) and GPT (Generative Pre-trained Trans-

former), are typically based on complex neural net-

works trained on extensive text datasets (Zhao et al.,

2023). Through training, these neural networks intri-

cate language features, including patterns, structures,

context, and semantics, enabling them to perform ad-

vanced such as text classiﬁcation, sentiment analysis,

translation, and question-answering (Radford et al.,

2019; Brown et al., 2020). LLMs have found ap-

plications in diverse domains, including software de-

velopment tasks like programming and code genera-

tion (Sadik et al., 2023b). However, their integration

into broader human-system, inter-system, and intra-

system interactions is still in its early stages. This

paper focuses on exploring this potential for broader

integration.

2.2 Holonic Architecture for System of

Systems

Holons are autonomous yet connected entities that

possess independent functionalities while contribut-

ing to a larger system (Koestler, 1968). Due to their

dual nature, holons are excellent for modeling the

heterogeneous CSs, accurately reﬂecting their inde-

pendent functions and contributions to the overall

SoS (Blair et al., 2015).

ICSOFT 2024 - 19th International Conference on Software Technologies

428

3 RELATED WORK

Nundloll et al. (2020) utilized this concept of using

holons to model IoT systems and introduced a frame-

work that describes holons using ontologies. Elhab-

bash et al. (2024) adapted this framework to the SoS

domain and proposed an SoS architecture where CSs

are modeled as ontological holons. This architecture

allows CSs to reason about and understand each other,

facilitating CS discovery, ad-hoc scalability, and dy-

namic SoS composition.

However, this architecture assumes that the onto-

logical descriptions of the holons are manually pro-

vided by vendors or systems engineers. Addressing

this limitation, Zhang et al. (2023) propose an NLP-

based approach that automatically extracts ontologi-

cal descriptions of IoT devices by scraping web data.

While this approach offers automation, the holonic ar-

chitecture for SoS still lacks capabilities for holon-

to-environment communication (Halba et al., 2021),

human-to-holon interaction, and communication with

unknown holons.

4 CONCEPTUAL FRAMEWORK

Our proposed framework aims to address the com-

munication challenges inherent in SoS by leveraging

NLP techniques with a particular focus on enabling

holon-to-holon and holon-to-human communication.

Figure 1 illustrates the framework depicting its com-

ponents and their interactions.

4.1 Overview

The framework involves a human operator who pro-

vides natural language instructions to the holons rep-

resenting the CS of an SoS. The instructions can range

from broad, high-level goals to speciﬁc tasks.

The CSs of the SoS are represented by holons

(e.g., Holon A and Holon B in Figure 1). Each holon

possesses speciﬁc capabilities or services, which are

the resources integrated into them. In addition, each

holon is also equipped with a localized NLP mod-

ule. These goals usually exceed the capabilities of

a single holon and require the collaboration of multi-

ple holons. The system then identiﬁes relevant holons

based on their capabilities and orchestrates their col-

laboration to achieve the operator’s objectives.

4.2 NLP Integration Module

This module is the core of the framework. This

module comprises three components: ontology-based

prompt engineering, an LLM, and an NLP communi-

cation interface.

4.2.1 Ontology-Based Prompt Engineering

This component is responsible for crafting precise

and contextually relevant prompts by incorporating

domain-speciﬁc ontologies. This ensures that the op-

erator’s inputs are tailored accurately to the speciﬁc

needs of the SoS domain, thereby enhancing the ef-

fectiveness and precision of the LLM’s response (Sec-

tion 4.2.2).

4.2.2 Large Language Model (LLM)

This component utilizes NLP capabilities to under-

stand and generate natural language interactions. It

interprets the reﬁned input from the prompt engineer-

ing component (Section 4.2.1), processes it, and con-

verts it into a syntax comprehensible to other hetero-

geneous holons of the SoS.

4.2.3 NLP Communication Interface

This interface translates the processed instructions

from the LLM into actionable commands for the

holons. These commands can activate or deacti-

vate the holons’ capabilities or services as needed to

achieve the overarching goal.

The NLP module provides feedback to the human

operator in the form of conﬁrmation messages, clari-

fying questions, or summaries of the intended actions.

This allows the operator to verify the system’s under-

standing and make any necessary corrections or re-

ﬁnements.

4.2.4 Holon-Level NLP

Each holon is equipped with a localized NLP mod-

ule, including a domain-speciﬁc LLM, enabling it to

understand and generate natural language instructions

for both human-holon and holon-holon interactions.

The human-holon communication occurs when the

NLP Integration Module interacts with the localized

NLP module of holons. The holon-to-holon interac-

tion facilitates the holons to coordinate and exchange

system descriptions of their encapsulated system with

other holons using natural language (NL). As appar-

ent in the Figure 1, the holon-to-holon interaction is

possible even without the NLP Integration module.

This distributed approach enhances autonomy and re-

duces reliance on a centralized module.

Enhancing Holonic Architecture with Natural Language Processing for System of Systems

429

Natural Language Interaction

Human

Operator

Refined prompt

Ontology-based Prompt

engineering

NLP Communication

Interface

Capabilities

Services

System of Systems

Holon A

Capabilities

Services

Holon B

Translates to/from actionable commands and holon descriptions

NL Communication

Large Language Model

LLM

Generate structured commands

Refine Instructions (if needed)

NLP Integration Module

Figure 1: The conceptual framework showing NLP integration with the Holonic Architecture.

4.3 Holon Composition and

Collaboration

Holons, utilizing their embedded NLP capabilities,

interact with each other and the central NLP mod-

ule to determine their capabilities and relevance to

the goal. Through an iterative negotiation process,

holons commit to providing speciﬁc services, while

others may be deemed irrelevant. The relevant holons

then form a holon composition, collaborating to fulﬁll

the given mission.

This approach streamlines the process of achiev-

ing complex goals within an SoS. Instead of requiring

in-depth knowledge of each constituent system, the

operator can simply communicate their intent in nat-

ural language, and the framework handles the rest.

5 CASE STUDY:

NLP-INTEGRATED UVF FOR

URBAN MOBILITY

5.1 Overview

This case study explores the integration of the pro-

posed NLP-enhanced holon communication frame-

work (Section 4) into smart city transportation us-

ing Unmanned Vehicle Fleets (UVF). The UVF, op-

erating within a dynamic environment, exempliﬁes an

SoS with complex interaction dynamics and scalabil-

ity challenges such as evolving missions, expanding

range and capacity demands, vehicle failures, and bat-

tery limitations (Sadik et al., 2023a). It comprises

several autonomous entities, including Unmanned

Ground Vehicles (UGVs) and Unmanned Aerial Ve-

hicles (UAVs), each functioning as a holon, operating

independently as well as collaborating to achieve the

ﬂeet’s overall objectives (Tchappi et al., 2020).

5.2 Scenario

Consider a scenario where a resident in a smart city

needs transportation from Position A to Position B.

The goal is to navigate the complex cityscape quickly

and efﬁciently, considering no-ﬂy zones, trafﬁc condi-

tions, and road layouts. This scenario presents several

challenges:

• Complex Urban Environment: Navigating

through a densely populated urban area with

varying altitudes and no-ﬂy zones for UAVs.

• Dynamic Routing: Adapting in real-time to trafﬁc

and environmental conditions to ensure the fastest

and safest route.

• Vehicle Coordination: Seamlessly transitioning

between UAVs and UGVs while maintaining a

consistent and comfortable experience.

• Communication: Ensuring clear and efﬁcient

communication between the user, UVs, and the

control center to manage expectations and adapt

to any changes in the mission.

5.3 NLP-Enhanced UVF

Communication

Figure 2 illustrates the integration of NLP module

(Section 4.2) into the UVF communication frame-

work. This integration enhances both human-to-ﬂeet

and intra-ﬂeet communications.

ICSOFT 2024 - 19th International Conference on Software Technologies

430

NLP Integration

Figure 2: Human-UV Interaction and Planning.

5.3.1 Human-UV Interaction

The user communicates their destination to the urban

mobility service using a natural language interface.

The NLP module’s ontology-based prompt engineer-

ing component (Section 4.2.1) reﬁnes this input, en-

suring it’s tailored to the UVF domain. The LLM

(Section 4.2.2) then interprets the request and initiates

mission planning.

5.3.2 Intra-Fleet Negotiation

To optimize efﬁciency, representative UVs from both

the UGV and UAV swarms are selected to interact

with the user and the urban mobility service. These

representatives use their localized NLP modules (Sec-

tion 4.2.3) to communicate with the rest of the ﬂeet,

negotiating roles, paths, and timing based on indi-

vidual capabilities, current status, and environmen-

tal factors. This negotiation process aligns with Sec-

tion 4.2.4 and Section 4.3 parts of the framework.

For example, the UAV representative communi-

cates its estimated time of arrival at the no-ﬂy zone

and available landing zones to the UGV representa-

tive. The UGV representative then analyzes potential

routes, considering trafﬁc conditions and road lay-

outs, and proposes a suitable landing zone and ren-

dezvous time. The UAV and UGV representatives it-

erate on this process until a mutually agreeable plan

is reached.

5.4 Resulting UVF Composition

Following the negotiation process, a UVF is formed

to accommodate the no-ﬂy zone (P

– P

in Figure 3).

This composition includes two UAVs for aerial seg-

ments and one UGV for ground transportation, show-

casing the dynamic SoS composition capability en-

abled by the framework. The UAV, upon reaching the

no-ﬂy zone, communicates with the UGV in natural

language, I am approaching the no-ﬂy zone. Please

prepare to receive the passenger at the designated

landing zone (Section 4.2.4). The UVs coordinate

seamlessly, ensuring a smooth transition for the user

at the landing and launch zones.

Upon reaching the predetermined landing zone

close to the user’s location (Position A), the ﬁrst UAV

communicates with the UGV to prepare for a smooth

transition to the no-ﬂy zone. The user is then trans-

ported by the UGV to a launch zone closer to his des-

tination, where the second UAV takes over to com-

plete the ﬁnal leg of the journey.

Figure 3: Resulting UVF of two UAVs and one UGV (P

—

is no-ﬂy zone).

Enhancing Holonic Architecture with Natural Language Processing for System of Systems

431

5.5 Mission Success Criteria

The success of the mission will be evaluated based on

the time taken to complete the mission, the number

of passengers successfully transported, the number of

successful negotiations among UVs, and the overall

satisfaction of the human operator with the system’s

performance. These metrics will provide valuable in-

sights into the effectiveness and usability of the NLP-

enhanced holonic architecture in real-world scenar-

ios.

6 EVALUATION

While this paper primarily focuses on presenting a

conceptual framework, we acknowledge the impor-

tance of evaluating its effectiveness in real-world sce-

narios. Future work will involve a rigorous evaluation

of the proposed NLP-enhanced holonic architecture

in a simulated environment, similar to the approach

used by (Sadik et al., 2023a). The implementation

can be done in by developing a multi-agent simulation

using a suitable framework (e.g., JADE), or a multi-

robot environment using ROS 2 and Gazebo to model

the interactions between the human operator, the NLP

module, and the holons.

Potential evaluation metrics could include:

• Task Completion Rate: The percentage of tasks

completed by the SoS using the NLP interface

compared to traditional methods.

• Communication Efﬁciency: The reduction in

communication overhead (e.g., message volume,

bandwidth usage) and time to complete tasks

achieved through NLP-based interaction.

• Communication Effectiveness: The percentage

of correctly interpreted user requests and holon-

generated instructions.

• Adaptability: The ability of the SoS to dynam-

ically reconﬁgure and adapt to changes in the

environment or mission objectives, facilitated by

NLP-based negotiation and coordination.

• Usability: Qualitative assessment of the ease of

use, intuitiveness, and user satisfaction of the NLP

interface for both human operators and holons.

By quantifying these metrics, we can assess the

impact of NLP integration on SoS performance and

identify areas for further improvement.

7 DISCUSSION

The integration of NLP within the holonic archi-

tecture offers several advantages that contribute to

the improved efﬁciency, adaptability, and usability of

SoS.

Firstly, by enabling natural language communi-

cation between the human operator and the holons,

the framework reduces the cognitive load on the op-

erator, who no longer needs to be familiar with the

speciﬁc syntax or protocols of each constituent sys-

tem. This streamlines the interaction process and al-

lows for more efﬁcient task assignment and coordina-

tion. Traditionally, achieving a goal in an SoS would

require the operator to be familiar with the internal

workings of each CS. The operator would then need

to orchestrate these CSs together to design an SoS that

accomplishes the goal.

Secondly, the use of NLP enables the holons to

dynamically negotiate and adapt their roles based on

the given goal and the capabilities of other holons.

This adaptability is crucial in complex and dynamic

SoS environments where the composition of holons

may change over time. Finally, the intuitive nature

of natural language interaction enhances the overall

usability of the SoS, making it more accessible to a

wider range of users, including those without special-

ized technical knowledge.

8 CONCLUSION AND FUTURE

WORK

This paper introduces a novel approach to enhance

holon communication within SoS through Natural

Language Processing, aiming to bridge the communi-

cation gap between human operators and holons, and

among holons themselves. The proposed framework

demonstrates the potential for NLP to improve the ef-

ﬁciency, adaptability, and usability of SoS, paving the

way for more intuitive and effective system-level col-

laboration.

Overall, this ﬁeld represents a promising area of

ongoing research, with future developments expected

to further reﬁne and validate the proposed model in

practical SoS applications. In the short term, lever-

aging the ROS2 platform (Daubaris et al., 2023),

we are currently implementing the proposed frame-

work using the Holon Programing Model (Ashfaq

et al., 2024) and system architectures for autonomous

robots (M

akitalo et al., 2021).

While the integration of LLMs into the holonic

architecture holds promise for enhancing interoper-

ability and adaptability, future research should also

ICSOFT 2024 - 19th International Conference on Software Technologies

432

address potential ethical concerns, such as privacy,

safety, and conﬂicts of interest (Rousi et al., 2023;

Levinson et al., 2024). Future work should also fo-

cus on addressing the challenges associated with nat-

ural language ambiguity, such as implementing clar-

iﬁcation dialogs. This can involve exploring the use

of domain-speciﬁc ontologies, controlled natural lan-

guages, clariﬁcation dialogs, and context-aware inter-

pretation. Additionally, there is a need to integrate

feedback mechanisms and validation techniques to

ensure robust and reliable communication within the

SoS, enabling continuous learning and improvement

of the NLP module.

REFERENCES

Ashfaq, M., Sadik, A. R., Mikkonen, T., Waseem,

M., and M

akitalo, N. (2024). The holon pro-

gramming model for heterogeneous and adap-

tive system of systems. TechRxiv preprint

10.36227/techrxiv.171387729.91629072/v2.

Blair, G., Bromberg, Y.-D., Coulson, G., Elkhatib, Y.,

eveill

ere, L., Ribeiro, H. B., Rivi

ere, E., and Ta

ıani,

F. (2015). Holons: Towards a systematic approach

to composing systems of systems. In 14th Interna-

tional Workshop on Adaptive and Reﬂective Middle-

ware, pages 1–6.

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D.,

Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G.,

Askell, A., et al. (2020). Language models are few-

shot learners. Advances in neural information pro-

cessing systems, 33:1877–1901.

Daubaris, P., Linkola, S., Kantosalo, A., and M

akitalo,

N. (2023). Getting started with ROS2 development:

A case study of software development challenges.

In 2023 IEEE/ACM 5th International Workshop on

Robotics Software Engineering, pages 37–44.

Elhabbash, A., Elkhatib, Y., Nundloll, V., Marco, V. S., and

Blair, G. S. (2024). Principled and automated system

of systems composition using an ontological architec-

ture. Future Generation Computer Systems, 157:499–

515.

Halba, K., Griffor, E., Lbath, A., and Dahbura, A. (2021).

A framework for the composition of IoT and CPS ca-

pabilities. In IEEE 45th Annual Computers, Software,

and Applications Conference, pages 1265–1272.

Jamshidi, M. (2008). Systems of systems engineering: Prin-

ciples and applications. CRC press.

Khurana, D., Koli, A., Khatter, K., and Singh, S. (2023).

Natural language processing: State of the art, current

trends and challenges. Multimedia tools and applica-

tions, 82(3):3713–3744.

Koestler, A. (1968). The ghost in the machine. Macmillan.

Koubaa, A. (2023). ROSGPT: Next-generation

human-robot interaction with ChatGPT and ROS.

Preprints.org, 2023:2023040827.

Levinson, L., Dietrich, M., Sarkisian, A., Sabanovic, S., and

Smart, W. D. (2024). Privacy aware robotics. In Com-

panion of the 2024 ACM/IEEE International Confer-

ence on Human-Robot Interaction, pages 1335–1337.

akitalo, N., Linkola, S., Laurinen, T., and M

annist

o, T.

(2021). Towards novel and intentional cooperation

of diverse autonomous robots: An architectural ap-

proach. In ECSA 2021 Companion, volume 2978 of

CEUR Workshop Proceedings.

Nielsen, C. B., Larsen, P. G., Fitzgerald, J., Woodcock, J.,

and Peleska, J. (2015). Systems of systems engineer-

ing: Basic concepts, model-based techniques, and re-

search directions. ACM Computing Surveys, 48(2):1–

41.

Nundloll, V., Elkhatib, Y., Elhabbash, A., and Blair, G. S.

(2020). An ontological framework for opportunistic

composition of IoT systems. In IEEE international

conference on informatics, IoT, and enabling tech-

nologies, pages 614–621.

Radford, A., Wu, J., Child, R., Luan, D., Amodei, D.,

Sutskever, I., et al. (2019). Language models are un-

supervised multitask learners. OpenAI blog, 1(8):9.

Rousi, R., Samani, H., M

akitalo, N., Vakkuri, V., Linkola,

S., Kemell, K.-K., Daubaris, P., Fronza, I., Mikko-

nen, T., and Abrahamsson, P. (2023). Business and

ethical concerns in domestic conversational genera-

tive ai-empowered multi-robot systems. In Interna-

tional Conference on Software Business, pages 173–

189. Springer Nature Switzerland Cham.

Sadik, A. R., Bolder, B., and Subasic, P. (2023a). A self-

adaptive system of systems architecture to enable its

ad-hoc scalability: Unmanned vehicle ﬂeet-mission

control center case study. In 7th International Confer-

ence on Intelligent Systems, Metaheuristics & Swarm

Intelligence, pages 111–118.

Sadik, A. R., Ceravola, A., Joublin, F., and Patra, J. (2023b).

Analysis of ChatGPT on source code. arXiv preprint

arXiv:2306.00597.

Tchappi, I. H., Galland, S., Kamla, V. C., Kamgang, J. C.,

Mualla, Y., Najjar, A., and Hilaire, V. (2020). A crit-

ical review of the use of holonic paradigm in trafﬁc

and transportation systems. Engineering Applications

of Artiﬁcial Intelligence, 90:103503.

Zhang, Z., Elkhatib, Y., and Elhabbash, A. (2023). NLP-

based generation of ontological system descriptions

for composition of smart home devices. In IEEE Inter-

national Conference on Web Services, pages 360–370.

Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y.,

Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang,

C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang,

X., Liu, Z., Liu, P., Nie, J.-Y., and Wen, J.-R. (2023).

A survey of large language models. arXiv preprint

arXiv:2303.18223.

Enhancing Holonic Architecture with Natural Language Processing for System of Systems

433