# SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance

arXiv: https://arxiv.org/abs/2405.19456 · HTML: https://mlsanity.com/paper/2405.19456/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 58 references that are in the map.
- First posted on arXiv 29 May 2024.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation](https://mlsanity.com/paper/2210.15718/) (2022)
- [Founder-GPT: Self-play to evaluate the Founder-Idea fit](https://mlsanity.com/paper/2312.12037/) (2023)
- [Improving Startup Success with Text Analysis](https://mlsanity.com/paper/2312.06236/) (2023)
- [Startup success prediction and VC portfolio simulation using CrunchBase data](https://mlsanity.com/paper/2309.15552/) (2023)

## Built on by (most cited first, 7 of 7)

- [Automating Venture Capital: Founder assessment using LLM-powered segmentation, feature engineering and automated labeling techniques](https://mlsanity.com/paper/2407.04885/) (2024)
- [Reasoning-Based AI for Startup Evaluation (R.A.I.S.E.): A Memory-Augmented, Multi-Step Decision Framework](https://mlsanity.com/paper/2504.12090/) (2025)
- [Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Method](https://mlsanity.com/paper/2408.09420/) (2024)
- [Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents](https://mlsanity.com/paper/2512.22608/) (2025)
- [The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction](https://mlsanity.com/paper/2512.23489/) (2025)
- [Can Large Language Models Improve Venture Capital Exit Timing After IPO?](https://mlsanity.com/paper/2601.00810/) (2025)
- [From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth](https://mlsanity.com/paper/2607.10972/) (2026)

## Abstract (arXiv)

LLM based agents have recently demonstrated strong potential in automating complex tasks, yet accurately predicting startup success remains an open challenge with few benchmarks and tailored frameworks. To address these limitations, we propose the Startup Success Forecasting Framework, an autonomous system that emulates the reasoning of venture capital analysts through a multi agent collaboration model. Our framework integrates traditional machine learning methods such as random forests and neural networks within a retrieval augmented generation framework composed of three interconnected modules: a prediction block, an analysis block, and an external knowledge block. We evaluate our framework and identify three main findings. First, by leveraging founder segmentation, startups led by L5 founders are 3.79 times more likely to succeed than those led by L1 founders. Second, baseline large language models consistently overpredict startup success and struggle under realistic class imbalances largely due to overreliance on founder claims. Third, our framework significantly enhances prediction accuracy, yielding a 108.3 percent relative improvement over GPT 4o mini and a 30.8 percent relative improvement over GPT 4o. These results demonstrate the value of a multi agent approach combined with discriminative machine learning in mitigating the limitations of standard large language model based prediction methods.