Founder-GPT: Self-play to evaluate the Founder-Idea fit
Not on the map. Why?
Abstract (arXiv)
This research introduces an innovative evaluation method for the "founder-idea" fit in early-stage startups, utilizing advanced large language model techniques to assess founders' profiles against their startup ideas to enhance decision-making. Embeddings, self-play, tree-of-thought, and critique-based refinement techniques show early promising results that each idea's success patterns are unique and they should be evaluated based on the context of the founder's background.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 5 of its 6 references that are in the map. First posted on arXiv 19 Dec 2023.
Builds on
5 of 6 references.
References · 5
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
- 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
- 2023Large Language Modelscited by 780
- 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
Built on by
Citing papers per year: 2024: 2; 2025: 3; 2026: 1.
6 papers.
- 2024SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performancecited by 7
- 2024Automating Venture Capital: Founder assessment using LLM-powered segmentation, feature engineering and automated labeling techniquescited by 4
- 2025Reasoning-Based AI for Startup Evaluation (R.A.I.S.E.): A Memory-Augmented, Multi-Step Decision Frameworkcited by 3
- 2026DIALECTIC: A Multi-Agent System for Startup Evaluationcited by 2
- 2025Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Datacited by 1
- 2025From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capitalcited by 0
- 2026DIALECTIC: A Multi-Agent System for Startup Evaluation19 Feb 2026
- 2025From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital9 Sep 2025
- 2025Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data30 May 2025
- 2025Reasoning-Based AI for Startup Evaluation (R.A.I.S.E.): A Memory-Augmented, Multi-Step Decision Framework16 Apr 2025
- 2024Automating Venture Capital: Founder assessment using LLM-powered segmentation, feature engineering and automated labeling techniques5 Jul 2024
- 2024SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance29 May 2024
Similar, not cited
Close in wording, no citation either way
- 2025LLM-AR: LLM-powered Automated Reasoning Framework
- 2026Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
- 2026Generative AI Fuels Solo Entrepreneurship, but Teams Still Lead at the Top
- 2022"I think this is the most disruptive technology": Exploring Sentiments of ChatGPT Early Adopters using Twitter Data
- 2026How Well Can AI Generate Backlogs from App Mockups?
- 2025CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction
- 2025Digital Co-Founders: Transforming Imagination into Viable Solo Business via Agentic AI
- 2026AI and Its Impact on Creativity and Diversity: An Empirical Study of LLM-Generated Product Ideas