Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69261
Volume:
10 |
11 |
Nov 2026
Pages:
1-12
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Sciences
AISSMS IOIT
Computer Sciences
AISSMS IOIT
Computer Sciences
AISSMS IOIT
Computer Sciences
AISSMS IOIT
Starting and growing a startup is a continuous chain of decisions across market validation, business modelling, finance, product, growth and operations, yet the Artificial Intelligence (AI) tools available to founders mostly address one of these tasks at a time, give generic advice and do not compare the plan with what actually happens. This paper reviews fifteen recent IEEE papers, supported by foundation work on Large Language Model (LLM) agents, Retrieval-Augmented Generation (RAG), graph-based orchestration and tree-based machine learning, along three technical themes: orchestration of specialised agents, evidence-grounded and explainable advice, and adaptive monitoring of planned against actual performance, with human oversight as a cross-cutting requirement. The review finds that machine-learning studies predict startup success or lifespan but stop at a prediction; early-stage multi-agent systems coordinate idea generation, market research and Minimum Viable Product (MVP) planning but give limited support after launch; the one reviewed marketing system adds founder approval before publishing but covers content only; and general agentic AI studies are not tied to the startup lifecycle. None of the reviewed papers combines dynamic agent selection by startup type and stage, financial and valuation analysis, explanation with confidence and alternatives under founder control, and continuous planned-versus-actual monitoring that re-triggers planning. The paper maps these gaps to a reference architecture built on a LangGraph orchestrator with seven specialised agents, discusses open challenges in data quality, LLM reliability, valuation and privacy, and outlines directions for future work. No new experimental results are reported; findings of the reviewed papers are stated as reported by their authors.
KEYWORDS
This paper reviewed fifteen recent IEEE papers and seven foundation references on AI-based startup decision support along four dimensions: orchestration, evidence-grounded advice, adaptive monitoring and human oversight. The reviewed work supports individual functions or the early stage and leaves the post-launch loop of monitoring and adaptation open. Prediction studies stop at a prediction, early-stage multi-agent systems concentrate on deliverables, the one marketing system with founder approval covers content only, and general agentic frameworks are not tied to the startup lifecycle. No reviewed paper combines dynamic orchestration, financial and valuation analysis, explainable advice under founder control and continuous planned-versus-actual monitoring. A single explainable, lifecycle-oriented platform built as specialised agents under one orchestrator, with the founder approving every recommendation, is the combination that remains to be built and measured, for both technology and non-technology startups.
[1] “Start-Wise AI: Predicting Startup Success or Failure Using Data-Driven Insights,” in Proc. IEEE ICETEMS, 2026, doi: 10.1109/ICETEMS66917.2026.11469447. (Author names and pages to be added from IEEE Xplore.) [2] “Agentic AI Startup Cofounder,” in Proc. IEEE CI2A, 2026, doi: 10.1109/CI2A69097.2026.11576988. (Author names and pages to be added; DOI to be verified, as it is identical to the DOI recorded for [3].) [3] “AI-Empowered System for Personalized Strategic Planning for Tech Startups,” in Proc. IEEE CI2A, 2026. (Author names, pages and DOI to be added from IEEE Xplore.) [4] “Autonomous Content Generation and Management for Startup Social Media Marketing using Agentic AI,” in Proc. 2026 2nd Int. Conf. Advances in Intelligent Computing and Applications (AICAPS), 2026, doi: 10.1109/AICAPS68631.2026.11453213. [5] “Agentic AI for Startup Growth and Business Decision Support,” IEEE, 2026. [6] “Machine Learning-Based Prediction of Startup Success and Using Founder’s Background and Funding Features,” IEEE, IEEE Xplore document 11325516. (Authors, venue, year, pages and DOI to be added from IEEE Xplore.) [7] “Predicting Success Rate of Startups using Machine Learning Algorithms,” IEEE, 2022, IEEE Xplore document 9908921. (Authors, venue, pages and DOI to be added from IEEE Xplore.) [8] “Machine Learning-based Start-up Company Lifespan Prediction: the Chinese Market as an Example,” IEEE, 2023, IEEE Xplore document 10185504. (Authors, venue, pages and DOI to be added from IEEE Xplore.) [9] G. Abhinand and B. N. Poonam, “An efficient stacking ensemble technique for success prediction of Indian ventures,” in Proc. 2022 Int. Conf. Data Science, Agents & Artificial Intelligence (ICDSAAI), IEEE, 2022, doi: 10.1109/ICDSAAI55433.2022.10028895. [10] “Start-Up Capital Estimation and Profitability Prediction for E-Commerce Start-Ups Using Machine Learning,” IEEE, 2024, doi: 10.1109/SEB4SDG60871.2024.10630338. (Authors, venue and pages to be added.)
Publication Date
11/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...