pith. sign in

arxiv: 2606.09182 · v1 · pith:7YG2OJDRnew · submitted 2026-06-08 · 💻 cs.SE

Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering

Kehui Chen , Yicheng Sun , Jacky Keung , Zhenyu Mao , Xiaoxue Ma This is my paper

Pith reviewed 2026-06-27 15:47 UTC · model grok-4.3

classification 💻 cs.SE
keywords Model Context ProtocolLLM-driven software engineeringenterprise adoptioninterview studydeployment challengesAI workflowsstandardizationtask coordination
0
0 comments X

The pith

Enterprises value the Model Context Protocol for LLM workflows but face barriers from ecosystem fragmentation and coordination issues.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper reports on interviews with practitioners to examine how the Model Context Protocol is actually used in companies applying LLMs to software engineering tasks. It establishes that MCP helps with cross-system collaboration, breaking tasks into parts, and reusing knowledge across tools, yet real deployment runs into problems with fragmented ecosystems, hard-to-coordinate components, and gaps in handling distributed state or diagnosing faults. The work also records calls for stronger standards and simpler entry points such as low-code options. These observations matter because LLMs are moving into complex, multi-tool development settings where protocols for context and coordination will shape whether the technology scales beyond prototypes.

Core claim

Semi-structured interviews with 20 practitioners from eight companies in the Internet and financial sectors show that the Model Context Protocol supports cross-system collaboration, task decoupling, and knowledge reuse in LLM-based workflows, but adoption stays limited by ecosystem fragmentation, cross-component coordination difficulties, and open problems in distributed state management and fault diagnosis, while participants seek better standardization and lower barriers through low-code or plugin approaches.

What carries the argument

Semi-structured interviews with 20 practitioners from eight companies that surface benefits and constraints of MCP use in enterprise LLM-driven software engineering.

If this is right

  • MCP enables cross-system collaboration, task decoupling, and knowledge reuse inside LLM-driven development workflows.
  • Ecosystem fragmentation and cross-component coordination remain the main practical obstacles to wider use.
  • Distributed state management and fault diagnosis stay unresolved and limit reliable operation.
  • Practitioners want stronger standardization to reduce integration effort.
  • Low-code or plugin-based methods would lower the barrier to entry for MCP.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same coordination and state-management frictions could appear in other regulated or data-heavy industries.
  • Targeted tooling for state tracking and fault diagnosis might directly address the reported operational gaps.
  • Standardization efforts could be prioritized by measuring how much fragmentation slows current MCP pilots.
  • Quantitative follow-up studies across more firms would test whether the reported demands for low-code support hold at scale.

Load-bearing premise

The views of the 20 interviewed practitioners from eight internet and financial companies represent the deployment challenges, operational risks, and expectations in broader enterprise adoption of MCP.

What would settle it

A larger survey or set of interviews across more companies and sectors that finds substantially different patterns of benefits or barriers would show the original sample is not representative.

Figures

Figures reproduced from arXiv: 2606.09182 by Jacky Keung, Kehui Chen, Xiaoxue Ma, Yicheng Sun, Zhenyu Mao.

Figure 1
Figure 1. Figure 1: Four Components of the MCP Protocol Unified context abstraction and encapsulation. MCP de￾fines a standardized, structured format for representing task context, including user preferences, tool execution history, and security policies, enabling consistent transmission and parsing of contextual information and avoiding incompatibilities in interaction formats. Decoupled layered architecture. As an independe… view at source ↗
Figure 2
Figure 2. Figure 2: The Overview of the Research Methodology [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Key Technical Bottlenecks of MCP Adoption [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Core Application Scenarios of MCP Workflows have been expanded to include MCP tool reg￾istration, protocol adaptation, and permission configuration, forming standardized processes from demand initiation to task execution. Collaboration models have shifted toward cross￾team and cross-model coordination: Internet teams adopt dis￾tributed MCP architectures to avoid single points of failure; FinTech teams brea… view at source ↗
Figure 5
Figure 5. Figure 5: Views on MCP Performance Improvements typically only requires registration, which lowers maintenance effort and reduces rental costs for medium- and large-scale projects. MCP-based architectures also have lower operat￾ing costs, help constrain improper operations, standardize workflows, and support fault isolation rules, whereas LLMs with function calling alone require additional custom secu￾rity logic. As… view at source ↗
Figure 6
Figure 6. Figure 6: LLM+Function Calling VS LLM+MCP 4.4 RQ4: What are participants’ expectations for MCP, and what challenges occur in multi-model collaboration? This research question explores participants’ common and industry-specific expectations for MCP, while analyzing the causes of the “stability superposition attenuation” phenomenon in MCP multi-model collaboration scenarios. Participants’ expectations mainly focus on … view at source ↗
read the original abstract

Large Language Models (LLMs) are increasingly used in AI-based software engineering, but their limitations in complex task execution and multi-tool coordination have driven growing interest in the Model Context Protocol (MCP). Existing research has mainly focused on MCP's technical design, with limited empirical evidence on how it is adopted and used in enterprise practice, particularly with regard to deployment challenges, operational risks, and practitioner expectations. To address this gap, we conducted semi-structured interviews with 20 practitioners from eight companies in the Internet and financial sectors. The findings show that MCP is valued for supporting cross-system collaboration, task decoupling, and knowledge reuse in LLM-based workflows, but its adoption remains constrained by ecosystem fragmentation, cross-component coordination difficulties, and unresolved problems in distributed state management and fault diagnosis. Participants also expressed strong demand for better standardization, lower adoption barriers through low-code or plugin-based approaches, and more systematic operational support. These results provide early empirical evidence on enterprise MCP practice and offer practical implications for improving MCP's standardization, usability, and deployment readiness in real-world software engineering environments.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper reports findings from semi-structured interviews with 20 practitioners from eight companies in the internet and financial sectors on enterprise adoption of the Model Context Protocol (MCP) for LLM-driven software engineering. It claims MCP supports cross-system collaboration, task decoupling, and knowledge reuse but faces barriers from ecosystem fragmentation, cross-component coordination, distributed state management, and fault diagnosis, with strong practitioner demand for standardization and low-code approaches; the work positions these as early empirical evidence on real-world MCP practice.

Significance. If the themes are robustly derived, the study supplies practitioner-grounded insights into MCP benefits and deployment frictions that could usefully inform protocol standardization and tooling priorities in AI-based software engineering.

major comments (2)
  1. [Abstract] Abstract: the claim that results characterize 'enterprise MCP practice' and 'real-world software engineering environments' rests on a sample drawn exclusively from internet and financial sectors across only eight firms; without evidence that this captures variation in scale, maturity, or domain, the reported barriers (fragmentation, coordination, state management) cannot be treated as MCP-intrinsic rather than sector-specific.
  2. [Methods] Methods description (as summarized): no information is supplied on interview protocol, participant selection criteria, coding process, or how raw responses map to the listed benefits and barriers, so it is not possible to evaluate whether the data support the central themes.
minor comments (1)
  1. [Abstract] Abstract: the phrasing 'early empirical evidence' could be qualified with an explicit statement of sample scope to avoid overgeneralization.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and commit to revisions that strengthen the manuscript's transparency and appropriate scoping of claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that results characterize 'enterprise MCP practice' and 'real-world software engineering environments' rests on a sample drawn exclusively from internet and financial sectors across only eight firms; without evidence that this captures variation in scale, maturity, or domain, the reported barriers (fragmentation, coordination, state management) cannot be treated as MCP-intrinsic rather than sector-specific.

    Authors: We agree the sample is restricted to internet and financial sectors across eight firms, limiting claims of broad generalizability. We will revise the abstract, introduction, and discussion to qualify all claims as applying specifically to these sectors and contexts, and add an explicit limitations paragraph noting that barriers may be sector-influenced rather than purely MCP-intrinsic. Future work across additional domains will be needed to assess broader applicability. revision: yes

  2. Referee: [Methods] Methods description (as summarized): no information is supplied on interview protocol, participant selection criteria, coding process, or how raw responses map to the listed benefits and barriers, so it is not possible to evaluate whether the data support the central themes.

    Authors: We will substantially expand the Methods section to detail the semi-structured interview protocol (including core questions), participant selection and recruitment criteria (roles, MCP experience threshold, company types), the thematic analysis procedure (including coding steps and how excerpts were mapped to themes), and any reliability checks. This will enable readers to assess how the data support the reported benefits and barriers. revision: yes

Circularity Check

0 steps flagged

No circularity: qualitative interview study with no derivations or fitted predictions

full rationale

The paper is a qualitative empirical study based on 20 semi-structured interviews. It contains no equations, parameters, predictions, or derivations that could reduce to inputs by construction. No self-citation chains, ansatzes, or uniqueness theorems are invoked as load-bearing elements. The central claims are direct reports of practitioner responses, making the work self-contained against external benchmarks with no circular steps present.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on the assumption that a small purposive sample of interviews captures representative enterprise experiences and that self-reported perceptions accurately reflect operational realities without significant bias.

axioms (1)
  • domain assumption Semi-structured interviews with 20 practitioners from eight companies provide reliable and generalizable insights into enterprise MCP adoption challenges and values.
    The study uses this sample to draw conclusions about broader practice and practitioner expectations.

pith-pipeline@v0.9.1-grok · 5726 in / 1244 out tokens · 22851 ms · 2026-06-27T15:47:08.844048+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Teaching Software Engineering with LLM and MCP Integration: From Classroom to Industry Practice

    cs.SE 2026-06 unverdicted novelty 2.0

    Describes an LLM-and-MCP-integrated collaborative teaching model intended to improve software engineering students' practical skills and industry readiness.

Reference graph

Works this paper leans on

44 extracted references · 3 linked inside Pith · cited by 1 Pith paper

  1. [1]

    Model context protocol (mcp): Landscape, secu- rity threats, and future research directions.arXiv preprint arXiv:2503.23278, 2025

    Xinyi Hou, Yanjie Zhao, Shenao Wang, and Haoyu Wang. Model context protocol (mcp): Landscape, secu- rity threats, and future research directions.arXiv preprint arXiv:2503.23278, 2025

    Pith/arXiv arXiv 2025

  2. [2]

    Introducing the model context protocol

    Anthropic. Introducing the model context protocol. Technical Report AN-2024-1125, Anthropic, 11 2024. Accessed: 2026-01-26

    2024

  3. [3]

    A survey of ai agent protocols

    Yingxuan Yang, Huacan Chai, Yuanyi Song, Siyuan Qi, Muning Wen, Ning Li, Junwei Liao, Haoyi Hu, Jianghao Lin, Gaowei Chang, et al. A survey of ai agent protocols. arXiv preprint arXiv:2504.16736, 2025

    arXiv 2025

  4. [4]

    Mcp-bench: Bench- marking tool-using llm agents with complex real-world tasks via mcp servers.arXiv preprint arXiv:2508.20453, 2025

    Zhenting Wang, Qi Chang, Hemani Patel, Shashank Biju, Cheng-En Wu, Quan Liu, Aolin Ding, Alireza Reza- zadeh, Ankit Shah, Yujia Bao, et al. Mcp-bench: Bench- marking tool-using llm agents with complex real-world tasks via mcp servers.arXiv preprint arXiv:2508.20453, 2025

    arXiv 2025

  5. [5]

    Haowen Xu, Yulin Sun, Jose Tupayachi, Olufemi Omi- taomu, Sisi Zlatanova, and Xueping Li. Towards the autonomous optimization of urban logistics: Training generative ai with scientific tools via agentic digital twins and model context protocol.arXiv preprint arXiv:2506.13068, 2025

    arXiv 2025

  6. [6]

    Securing the model context protocol: Defending llms against tool poisoning and adversarial attacks.Journal of the ACM (JACM), 37(4):111:1– 111:13, 2025

    Anonymous. Securing the model context protocol: Defending llms against tool poisoning and adversarial attacks.Journal of the ACM (JACM), 37(4):111:1– 111:13, 2025

    2025

  7. [7]

    Enterprise- grade security for the model context protocol (mcp): Frameworks and mitigation strategies.arXiv preprint arXiv:2504.08623, 2025

    Vineeth Sai Narajala and Idan Habler. Enterprise- grade security for the model context protocol (mcp): Frameworks and mitigation strategies.arXiv preprint arXiv:2504.08623, 2025

    arXiv 2025

  8. [8]

    Mcp: A security testing tool driven by require- ments

    Phu X Mai, Fabrizio Pastore, Arda Goknil, and Lionel C Briand. Mcp: A security testing tool driven by require- ments. In2019 IEEE/ACM 41st International Confer- ence on Software Engineering: Companion Proceedings (ICSE-Companion), pages 55–58. IEEE, 2019

    2019

  9. [9]

    Se- curing the model context protocol (mcp): Risks, controls, and governance.arXiv preprint arXiv:2511.20920, 2025

    Herman Errico, Jiquan Ngiam, and Shanita Sojan. Se- curing the model context protocol (mcp): Risks, controls, and governance.arXiv preprint arXiv:2511.20920, 2025

    arXiv 2025

  10. [10]

    Toolace: Winning the points of llm function calling.arXiv preprint arXiv:2409.00920, 2024

    Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Zhengy- ing Liu, Yuanqing Yu, et al. Toolace: Winning the points of llm function calling.arXiv preprint arXiv:2409.00920, 2024

    arXiv 2024

  11. [11]

    Towards AI, Inc., 2024

    Louis-Franc ¸ois Bouchard and Louie Peters.Building LLMs for production: enhancing LLM abilities and re- liability with prompting, fine-tuning, and RAG. Towards AI, Inc., 2024

    2024

  12. [12]

    Large language model-brained gui agents: A survey.arXiv preprint arXiv:2411.18279, 2024

    Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, Qingwei Lin, et al. Large language model-brained gui agents: A survey.arXiv preprint arXiv:2411.18279, 2024

    Pith/arXiv arXiv 2024

  13. [13]

    An llm compiler for parallel function calling

    Sehoon Kim, Suhong Moon, Ryan Tabrizi, Nicholas Lee, Michael W Mahoney, Kurt Keutzer, and Amir Gholami. An llm compiler for parallel function calling. InForty- first International Conference on Machine Learning, 2024

    2024

  14. [14]

    Function calling in large language models: Industrial practices, challenges, and future directions.ACM Computing Surveys, 2025

    Maolin Wang, Yingyi Zhang, Bowen Yu, Bingguang Hao, Cunyin Peng, Yicheng Chen, Wei Zhou, Jinjie Gu, Chenyi Zhuang, Ruocheng Guo, et al. Function calling in large language models: Industrial practices, challenges, and future directions.ACM Computing Surveys, 2025

    2025

  15. [15]

    Introduction to langchain framework.Textual Intelligence: Large Lan- guage Models and Their Real-World Applications, pages 253–285, 2025

    Deepti Goyal and Amita Gautam. Introduction to langchain framework.Textual Intelligence: Large Lan- guage Models and Their Real-World Applications, pages 253–285, 2025

    2025

  16. [16]

    Au- toagents: A framework for automatic agent generation

    Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, B ¨orje F Karlsson, Jie Fu, and Yemin Shi. Au- toagents: A framework for automatic agent generation. arXiv preprint arXiv:2309.17288, 2023

    arXiv 2023

  17. [17]

    Mao: A framework for process model generation with multi-agent orchestration.IEEE Trans- actions on Services Computing, 2025

    Leilei Lin, Yumeng Jin, Yingming Zhou, Wenlong Chen, and Chen Qian. Mao: A framework for process model generation with multi-agent orchestration.IEEE Trans- actions on Services Computing, 2025

    2025

  18. [18]

    Connecting mod- els, data, and concepts to understand fragmentation’s ecosystem-wide effects, 2017

    Nick M Haddad, Robert D Holt, Robert J Jr Fletcher, Michel Loreau, and Jean Clobert. Connecting mod- els, data, and concepts to understand fragmentation’s ecosystem-wide effects, 2017

    2017

  19. [19]

    Evaluation report on mcp servers.arXiv preprint arXiv:2504.11094, 2025

    Zhiling Luo, Xiaorong Shi, Xuanrui Lin, and Jinyang Gao. Evaluation report on mcp servers.arXiv preprint arXiv:2504.11094, 2025

    arXiv 2025

  20. [20]

    Mcpsecbench: A systematic security benchmark and playground for testing model context protocols

    Yixuan Yang, Daoyuan Wu, and Yufan Chen. Mcpsecbench: A systematic security benchmark and playground for testing model context protocols. arXiv preprint arXiv:2508.13220, 2025

    arXiv 2025

  21. [21]

    Mcpeval: Auto- matic mcp-based deep evaluation for ai agent models

    Zhiwei Liu, Jielin Qiu, Shiyu Wang, Jianguo Zhang, Zuxin Liu, Roshan Ram, Haolin Chen, Weiran Yao, Shelby Heinecke, Silvio Savarese, et al. Mcpeval: Auto- matic mcp-based deep evaluation for ai agent models. In Proceedings of the 2025 Conference on Empirical Meth- ods in Natural Language Processing: System Demonstra- tions, pages 373–402, 2025

    2025

  22. [22]

    Livemcpbench: Can agents navigate an ocean of mcp tools?arXiv preprint arXiv:2508.01780, 2025

    Guozhao Mo, Wenliang Zhong, Jiawei Chen, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. Livemcpbench: Can agents navigate an ocean of mcp tools?arXiv preprint arXiv:2508.01780, 2025

    arXiv 2025

  23. [23]

    Energyplus-mcp: A model-context-protocol server for ai-driven building energy modeling.SoftwareX, 32:102367, 2025

    Han Li, Yujie Xu, and Tianzhen Hong. Energyplus-mcp: A model-context-protocol server for ai-driven building energy modeling.SoftwareX, 32:102367, 2025

    2025

  24. [24]

    Beyond formal semantics for capabilities and skills: Model context protocol in manufacturing.arXiv preprint arXiv:2506.11180, 2025

    Luis Miguel Vieira da Silva, Aljosha K ¨ocher, and Felix Gehlhoff. Beyond formal semantics for capabilities and skills: Model context protocol in manufacturing.arXiv preprint arXiv:2506.11180, 2025

    arXiv 2025

  25. [25]

    Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents

    Yuyou Gan, Yong Yang, Zhe Ma, Ping He, Rui Zeng, Yiming Wang, Qingming Li, Chunyi Zhou, Songze Li, Ting Wang, et al. Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents. arXiv preprint arXiv:2411.09523, 2024

    arXiv 2024

  26. [26]

    Model context protocol (mcp) at first glance: Studying the security and maintainability of mcp servers

    Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh, Gopi Krishnan Rajbahadur, Bram Adams, and Ahmed E Hassan. Model context protocol (mcp) at first glance: Studying the security and maintainability of mcp servers. arXiv preprint arXiv:2506.13538, 2025

    Pith/arXiv arXiv 2025

  27. [27]

    When mcp servers attack: Tax- onomy, feasibility, and mitigation.arXiv preprint arXiv:2509.24272, 2025

    Weibo Zhao, Jiahao Liu, Bonan Ruan, Shaofei Li, and Zhenkai Liang. When mcp servers attack: Tax- onomy, feasibility, and mitigation.arXiv preprint arXiv:2509.24272, 2025

    arXiv 2025

  28. [28]

    Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1– 36, 2025

    Zehang Deng, Yongjian Guo, Changzhou Han, Wanlun Ma, Junwu Xiong, Sheng Wen, and Yang Xiang. Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1– 36, 2025

    2025

  29. [29]

    Mcp-riskcue: Can llm infer risk information from mcp server system logs?arXiv preprint arXiv:2511.05867, 2025

    Jiayi Fu and Qiyao Sun. Mcp-riskcue: Can llm infer risk information from mcp server system logs?arXiv preprint arXiv:2511.05867, 2025

    arXiv 2025

  30. [30]

    Research and scholarly methods: Semi-structured inter- views.Journal of the american college of clinical pharmacy, 4(10):1358–1367, 2021

    Omolola A Adeoye-Olatunde and Nicole L Olenik. Research and scholarly methods: Semi-structured inter- views.Journal of the american college of clinical pharmacy, 4(10):1358–1367, 2021

    2021

  31. [31]

    Sampling in software engineering research: A critical review and guidelines

    Sebastian Baltes and Paul Ralph. Sampling in software engineering research: A critical review and guidelines. Empirical Software Engineering, 27(4):94, 2022

    2022

  32. [32]

    Prac- titioners’ expectations on log anomaly detection.IEEE Transactions on Software Engineering, 2025

    Xiaoxue Ma, Yishu Li, Jacky Keung, Xiao Yu, Huiqi Zou, Zhen Yang, Federica Sarro, and Earl T Barr. Prac- titioners’ expectations on log anomaly detection.IEEE Transactions on Software Engineering, 2025

    2025

  33. [33]

    How to interview

    Walter V Bingham and Bruce Victor Moore. How to interview. 1931

    1931

  34. [34]

    Percep- tions, practices, and gaps in osteomyelitis care in rural rwanda: insights from patients and healthcare workers

    Jean Paul Nsengiyumva, Theogene Kubahoniyesu, Eleazar Ndabarora, and Bernard Umutoniwase. Percep- tions, practices, and gaps in osteomyelitis care in rural rwanda: insights from patients and healthcare workers. BMC Health Services Research, 2026

    2026

  35. [35]

    Fashion Institute of Technology, State University of New York, 2014

    Muoi Le.Loaded gun: Open-ended questions. Fashion Institute of Technology, State University of New York, 2014

    2014

  36. [36]

    An Interview Study on MCP Expectations

    Anonymity. An Interview Study on MCP Expectations. 2 2026

    2026

  37. [37]

    Combining qualitative and quan- titative research within mixed method research designs: a methodological review.International journal of nursing studies, 48(3):369–383, 2011

    Ulrika ¨Ostlund, Lisa Kidd, Yvonne Wengstr ¨om, and Neneh Rowa-Dewar. Combining qualitative and quan- titative research within mixed method research designs: a methodological review.International journal of nursing studies, 48(3):369–383, 2011

    2011

  38. [38]

    Rosenfeld Media, 2009

    Donna Spencer.Card sorting: Designing usable cate- gories. Rosenfeld Media, 2009

    2009

  39. [39]

    Quantitative analysis.Journal of the Ex- perimental Analysis of Behavior, 42(3):421–434, 1984

    John A Nevin. Quantitative analysis.Journal of the Ex- perimental Analysis of Behavior, 42(3):421–434, 1984

    1984

  40. [40]

    From llms to llm-based agents for software engineering: A survey of current, challenges and future.arXiv preprint arXiv:2408.02479, 2024

    Haolin Jin, Linghan Huang, Haipeng Cai, Jun Yan, Bo Li, and Huaming Chen. From llms to llm-based agents for software engineering: A survey of current, challenges and future.arXiv preprint arXiv:2408.02479, 2024

    arXiv 2024

  41. [41]

    Digitalization of management processes in small and medium-sized enterprises—an overview of low-code and no-code platforms.Applied Sciences, 13(24):13078, 2023

    Roman Doma ´nski, Hubert Wojciechowski, Jacek Lewandowicz, and Łukasz Hada ´s. Digitalization of management processes in small and medium-sized enterprises—an overview of low-code and no-code platforms.Applied Sciences, 13(24):13078, 2023

    2023

  42. [42]

    Developing and managing software com- ponents in an ontology-based application server

    Daniel Oberle, Andreas Eberhart, Steffen Staab, and Raphael V olz. Developing and managing software com- ponents in an ontology-based application server. In ACM/IFIP/USENIX International Conference on Dis- tributed Systems Platforms and Open Distributed Pro- cessing, pages 459–477. Springer, 2004

    2004

  43. [43]

    Practitioners’ expectations on code completion.arXiv preprint arXiv:2301.03846, 2023

    Chaozheng Wang, Junhao Hu, Cuiyun Gao, Yu Jin, Tao Xie, Hailiang Huang, Zhenyu Lei, and Yuetang Deng. Practitioners’ expectations on code completion.arXiv preprint arXiv:2301.03846, 2023

    arXiv 2023

  44. [44]

    A language model for statements of software code

    Yixiao Yang, Yu Jiang, Ming Gu, Jiaguang Sun, Jian Gao, and Han Liu. A language model for statements of software code. In2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE), pages 682–687. IEEE, 2017

    2017