# LLM-SAA: LLM-persona Generated Distributions for Decision-making

arXiv: https://arxiv.org/abs/2602.06357 · HTML: https://mlsanity.com/paper/2602.06357/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents](https://mlsanity.com/paper/2502.15840/) (2025)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [Large Language Models for Market Research: A Data-augmentation Approach](https://mlsanity.com/paper/2412.19363/) (2024)
- [Human Simulacra: Benchmarking the Personification of Large Language Models](https://mlsanity.com/paper/2402.18180/) (2024)
- [Auto-Formulating Dynamic Programming Problems with Large Language Models](https://mlsanity.com/paper/2507.11737/) (2025)
- [How Big Should Your Data Really Be? Data-Driven Newsvendor: Learning One Sample at a Time](https://mlsanity.com/paper/2107.02742/) (2021)
- [Optimal Pricing with a Single Point](https://mlsanity.com/paper/2103.05611/) (2021)
- [Large Language Newsvendor: Decision Biases and Cognitive Mechanisms](https://mlsanity.com/paper/2512.12552/) (2025)
- [Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control](https://mlsanity.com/paper/2601.00121/) (2025)
- [OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making](https://mlsanity.com/paper/2505.13580/) (2025)

## Built on by (most cited first, 3 of 3)

- [AI Agents for Inventory Control: Human-LLM-OR Complementarity](https://mlsanity.com/paper/2602.12631/) (2026)
- [The Value of Information in Resource-Constrained Pricing](https://mlsanity.com/paper/2603.24974/) (2026)
- [LLM Biases](https://mlsanity.com/paper/2604.26960/) (2026)

## Abstract (arXiv)

LLMs can generate a wealth of data, ranging from simulated personas imitating human valuations and preferences, to demand forecasts based on world knowledge. But how well do such LLM-generated distributions support downstream decision-making? For example, when pricing a new product, a firm could prompt an LLM to simulate how much consumers are willing to pay based on a product description, but how useful is the resulting distribution for optimizing the price? We refer to this approach as LLM-SAA, in which an LLM is used to construct an estimated distribution and the decision is then optimized under that distribution. In this paper, we study metrics to evaluate the quality of these LLM-generated distributions, based on the decisions they induce. Taking three canonical decision-making problems (assortment optimization, pricing, and newsvendor) as examples, we find that LLM-generated distributions are practically useful, especially in low-data regimes. We also show that decision-agnostic metrics such as Wasserstein distance can be misleading when evaluating these distributions for decision-making.