A Survey on Intent-Based Networking
The DOI matches its Crossref record; 127 of the 127 references it cites were found in a registry or an index.
Abstract
Current and future network services and applications are expected to revolutionize our society and lifestyle. At the same time, the abundant possibilities that new network technologies offer to end users, network operators and administrators have created a cumbersome network configuration process to accommodate all different stakeholders and applications. Thus, lately, there is a need to simplify the management and configuration of the network, through possibly an autonomic and automatic way. Intent Based Networking (IBN) is such a paradigm that envisions flexible, agile, and simplified network configuration with minimal external intervention. This paper provides a detailed survey of how the IBN concept works and what are the main components to guarantee a fully autonomous IBN system (IBNS). Particular emphasis is given on the intent expression, intent translation, intent resolution, intent activation and intent assurance components, which form the closed loop automation system of an IBNS. The survey concludes with identifying open challenges and future directions of the problem at hand.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Intent-based networking tackles this challenge through employing closed-loop transformation, execution, and monitoring, rather than relying on a single translation step [15].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [15]
In the citing paper
“A second shared primitive is mismatch between what is intended and what is actually realised [15], [1].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [15]
In the citing paper
“Natural language intent is typically underspecified, even when expressed by experienced operators [28], [16], [15], [114].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [15]
In the citing paper
“NetOps is a natural target for agentic systems because many operational tasks already follow a repeatable loop: (i) gather evidence from measurement and control-plane state, (ii) form a hypothesis about a failure or a policy violation, (iii) propose a change, and (iv) validate the change before rollout [28], [16], [15], [55], [70].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [15]
In the citing paper
“Intent-based networking is typically conceptualised as a closed-loop system that provides continuous assurance, rather than as a single compilation step [15], [28], [16].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [15]
Citations
Cites
McKeown (2008) · doi:10.1145/1355734.1355746 · Cited by 8,513 · cited 1×
“OpenFlow [32] is one of the most used SDN protocols and rely on the notion of flow tables.”
MethodThe vision of autonomic computing
Kephart, J. O., & Chess, D. M. (2003) · Computer · doi:10.1109/mc.2003.1160055 · Cited by 6,572 · cited 2×
“Finally, we cannot omit what was accurately stated in [22], back in 2003: “As automation technologies improve, and our faith in them grows, we will entrust autonomic systems with making lower-level decisions”, but as also stated this journey would last many years.”
BackgroundSoftware-Defined Networking: A Comprehensive Survey
Kreutz, D., Ramos, F. M. V., Esteves Verissimo, P., Esteve Rothenberg, C., Azodolmolky, S., & Uhlig, S. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2014.2371999 · Cited by 5,050
P4: programming protocol-independent packet processors
Bosshart, P., Daly, D., Gibb, G., Izzard, M., McKeown, N., Rexford, J., Schlesinger, C., Talayco, D., Vahdat, A., Varghese, G., et al. (2014) · ACM SIGCOMM Computer Communication Review · doi:10.1145/2656877.2656890 · Cited by 2,867 · cited 1×
“P4 can be seen as a packet programming language and an evolution of OpenFlow, that can act as an interface between the controller and the switches [33].”
BackgroundA Survey on Deep Learning for Named Entity Recognition
Li, J., Sun, A., Han, J., & Li, C. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2981314 · Cited by 1,567 · cited 2×
“In this case, the most useful named entities will be extracted and classified into predetermined categories, such as names, organization, location, etc. [54].”
BackgroundONOS: towards an open, distributed SDN OS
Berde, P., Gerola, M., Hart, J., Higuchi, Y., Kobayashi, M., Koide, T., Lantz, B., O'Connor, B., Radoslavov, P., Snow, W., et al. (2014) · Proceedings of the third workshop on Hot topics in software defined networking · doi:10.1145/2620728.2620744 · Cited by 1,118 · cited 1×
“ONOS [34] is a java-based, distributed and open source SDN controller initially designed for large networks to provide high speed and performant networks.”
BackgroundA Survey on Software-Defined Networking
Xia, W., Wen, Y., Foh, C. H., Niyato, D., & Xie, H. (2015) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2014.2330903 · Cited by 1,096
Service Function Chaining (SFC) Architecture
(2015) · doi:10.17487/rfc7665 · Cited by 659 · cited 1×
“NFV is also closely related with the Network Service Chaining paradigm [43].”
BackgroundA survey of autonomic communications
Dobson, S., Denazis, S., Fernández, A., Gaïti, D., Gelenbe, E., Massacci, F., Nixon, P., Saffre, F., Schmidt, N., & Zambonelli, F. (2006) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/1186778.1186782 · Cited by 626 · cited 1×
“Later on, alternative methods were investigated including game theory and economic models that were able to capture the interaction between different network control levels [25].”
MethodBenzaid, C., & Taleb, T. (2020) · IEEE Network · doi:10.1109/mnet.001.1900252 · Cited by 314 · cited 1×
“However, it is a very important aspect in networking since very often a network service needs to traverse multiple domains (e.g., enterprise, SD-WAN, core, etc.) [143].”
Background
Research works printed but not linked: 16
- Nefkens, 2019, Transforming Campus Networks to Intent-Based Networking
- Horn, 2001, Autonomic Computing: IBM’s Perspective on the State of Information Technology
- 2022, OpenDaylight
- 2022, Interacting With ONOS
- 2022, OpenDaylight User Guide
- Chiosi, 2012, Network functions virtualisation: An introduction, benefits, enablers, challenges and call for action
- 2012, Cisco NFV solution: Enabling rapid service innovation in the era of virtualization
- 2020, Generic Network Slice Template
- 2022, DialogFlow
- 2022, Enabling Interactions With Bots
- Jain, 2020, Intent-based, voice-assisted, self-healing SDN framework, J. Netw. Commun. Emerg. Technol., 10, 1
- 2022, Alexa Skills Kit
- Xia, 2016, NEMO (Networking Modeling) Language
- Janz, 2016, Intent NBI—Definition and Principles
- 2021, Network Functions Virtualization (NFV) Release 4; Management and Orchestration; Network Service Templates Specification
- 2021, Experiential Networked Intelligence (ENI); InTent Aware Network Autonomicity (ITANA) V2.1.1
Cited by
Items 301–327 of 327
Network security misconfigurations in Spanish organisations: An empirical study
Álvarez, D., Nuño, P., Bulnes, F. G., & Granda, J. C. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112631
Wang, J., Li, F., Liu, W., Pan, C., & Ren, H. (2026) · IEEE Wireless Communications · doi:10.1109/mwc.2026.3713852 · Cited by 1
“This shortens decision-making time and lets the agent manage key ISAC trade-offs, such as sensing accuracy versus communication throughput or reliability, in a context-aware way rather than maximizing a single KPI [5].”
Won, D., Dang, T. T.-A., Dinh, T. T. T., Wondmagegn, A. B., Tran, H. H., Lee, S., Kim, J., Tran, K. N. T., & Cho, S. (2026) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn69619.2026.11628683
Poster: ADN: Agent-Defined Networking
Varkey, S., & Choi, S. (2026) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3789240.3830286
“Intent-based networking (IBN) [3] narrows this gap, but still requires formal rule templates and significant manual effort.”
IntentP4: Bridging P4 Temporal Specifications and Executable Network Tests
Feng, R., Zhang, M., Jiang, Y., Gao, S., Liu, Y., & Zhang, S. (2026) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3789240.3822363
Herrera, L.-C., Janulevičius, J., Pinto, A., & Donoso, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3724564
“Intent-based networking [16], [17], [56] articulates a closed-loop translation from operator intent to network configuration over a continuously observed substrate.”
Li, K., Liu, J., Zhu, X., Zhang, C., Li, Z., & Wang, Z. (2026) · ICT Express · doi:10.1016/j.icte.2026.08.006
Lackinger, A., Morichetta, A., & Dustdar, S. (2026) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud72782.2026.00012
“The decisionMaker component, which is the coor-IntentFulfillment dination component this work focuses on, receives a global intent from the IntentTranslation component, which translates a natural-language intent into an operable, measurable one (cf. TMForum [32]) [11], [33].”
AUTOMATED COMPLIANCE CONTROL OF NETWORK DEVICE CONFIGURATIONS WITH CYBERSECURITY REQUIREMENTS
Sashnova, M., Vozniuk, Y., Cherkasov, D., & Maslov, P. (2026) · Collection of scientific works of the Military Institute of Kyiv National Taras Shevchenko University · doi:10.17721/2519-481x/2026/90-07
Enhancing Intent Understanding in Telecommunication-Specific Applications of LLMs
Tóthfalusi, T., Török, C., Kővári, Á., Hegedűs, C., & Pal, V. (2026) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms69089.2026.11668318
“Since the early 2020s, there are papers surveying various interpretations and implementations of the IBN idea [2], and especially its usage in network management [3].”
From Brownfield CLI to Intent Models: A Guardrailed Agentic Translation Workflow
Suvarna, N., Pappu, K., Sharma, S., & Ageze, B. (2026) · Conference on Local Computer Networks · doi:10.1109/lcn67947.2026.11660787
Cui, X., Tang, X., Wang, Y., Xu, X., Fan, X., & Huangfu, W. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3731467
“This paradigm is exemplified by network slicing in 5G/6G systems and aligns with broader trends like polymorphic or intent-based networking, where the network configuration adapts to the intent of the applications [5], [6].”
CognitiveContinuum: Intent-Aware Orchestration Using LLM and Fuzzy Logic
Akbari, N., Toosi, A. N., Grundy, J., & Cheema, M. A. (2026) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00045
“A key limitation is an orchestration model that aligns system behavior with human goals [10].”
Li, Q., Yang, X.-H., Qin, Y.-H., Zhou, Y.-S., Li, Z.-H., Luo, L., & Yu, H.-F. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-5015-4
“Intent-based networking (IBN) automatically configures networks from user intents, improving the efficiency of network setup and management [3,4].”
Small Language Models Fine-Tuning to Enable Intent-Driven Management of Kubernetes Resources
Brodimas, D., Polymanakos, G., Birbas, M., & Birbas, A. N. (2026) · IEEE Access · doi:10.1109/access.2026.3732477
“In the context of intent-based management, an intent is a declarative specification of the desired operational goals and outcomes of a system, without prescribing the low-level procedures or configurations required to achieve them [1].”
Sarwar, M. M. S., Kari, M. I., Khot, M. S. A. A., Hussain, S. A., Uddin, A. J., & Zameer, A. (2026) · MEC International Conference on Big Data and Smart City (ICBDSC) · doi:10.1109/icadaai64945.2026.11679252
Enabling Agentic AI across the Cloud-Edge Computing Continuum: A Research Roadmap
Prodan, R., Song, H., Göknil, A., Roman, D., Fazio, M. C., Villari, M., Mecella, M., Doborjeh, M., Kasabov, N. K., Ko, J., et al. (2026) · Annals of Computer Science and Information Systems · doi:10.15439/2026f0210
“AI further enables intent-based network [26] and continuum [27] management, in which stakeholders describe their desired outcomes while delegating the selection of an appropriate solution to AI.”
A Reusable Network Digital Twin Architecture for QoS-Centric Network Management
Zalat, M., Barber, C., Esfandiari, B., & Kunz, T. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3737654
“…important direction is expanding the range of management tasks that can be expressed as QoS-oriented optimization/diagnosis problems and integrating NDTs with intent-based interfaces (Intent-Based Networking (IBN)) [41] so that operator goals can be translated into new NDT/NDS instances on demand.”
Melnyk, A., Shcherbiak, I., Mudrak, M., Yurchyshyn, T., Nemeryshyn, V., & Vrabeľ, M. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700057
“The former is responsible for retrieving relevant knowledge fragments from the ontology, while the latter performs logical inference and verifies the consistency of the semantic model prior to test item generation [39, 40].”
Architecture of a Corporate Network Management System Based on a Knowledge-Oriented Approach
Melnyk, A., Popyk, Y., Romanets, I., Banasik, A., Maslyiak, B., & Сіткар, Т. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700093
“The development of Software-Defined Networking (SDN), Network Function Virtualization (NFV), Intent-Based Networking (IBN), and autonomous network management concepts has significantly expanded the capabilities for network infrastructure automation [6-8].”
Network Configuration Translation: A Survey of Symbolic, Neural, Hybrid, and Agentic Approaches
Shi, H., Gao, X., Yan, F., Lv, W., & Pang, R. (2026) · IEEE Access · doi:10.1109/access.2026.3738856
Distributed Artificial Intelligence for Agentic Intent-Based Networking in Mobile Networks
Ioannou, I. I., Naegele-Jackson, S., Filiposka, S., Burkard, V., Georgiades, M., Mackay, M., & Vassiliou, V. (2026) · Future Internet · doi:10.3390/fi18100530
Next-Generation eHealth Networking: AI-Driven Intent-Based Resilience for IoMT
Gharbaoui, M., Sahu, S. K., & Castoldi, P. (2026) · International Conference on Transparent Optical Networks · doi:10.1109/icton71309.2026.11705149
Intent-Driven Network CoPilot: Updating Cross-Protocol Configurations for Edge Service Guarantee
Qi, Q., Han, R., Sun, H., He, B., Shi, Y., Wan, Z., Zhuang, Z., Liao, J., Li, T., & Wang, J. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3739971
“This requires that network behaviors not only satisfy connectivity policies but also closely align with users quality of service (QoS) experiences [2], [4].”
Unified Modeling and Policy Normalization Analysis Method for Heterogeneous Network Devices
Chen, K., Gao, Q., 陈其伟, Jiang, H., & Chen, Y. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-1678-9_54
Pendyala, B. P., & Praveen, P. (2026) · International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI) · doi:10.1109/icoici69824.2026.11724041
“Reinforcement-learning algorithms, particularly PPO, provide a practical basis for adaptive decision-making in non-stationary environments [11], but the policy must be coupled with intent modeling, dependency-sensitive reasoning, and explicit safety constraints [12].”
Metadata
- Authors
- Leivadeas, A., & Falkner, M.
- Affiliations
- École de Technologie Supérieure (CA)
- Cisco Systems (Canada) (CA)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2023
- Volume
- 25
- Issue
- 1
- Pages
- 625-655
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W4312980540
- Cited by
- 326
- References
- 127
- Citations by year
- 2026: 92 · 2025: 126 · 2024: 72 · 2023: 36
- FWCI
- 25.96
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion)
- Espace ÉTS (ETS) (submittedVersion)
- Funders
- Cisco University Research Program Fund of Silicon Valley Community Foundation (2021-234759 (3696))
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Optical Network Technologies
- Physical Sciences › Computer Science › Computer Networks and Communications › Mobile Agent-Based Network Management
- Keywords
- intent-based networking, network configuration automation, autonomic networks, intent translation, network management
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.