# Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)

arXiv: https://arxiv.org/abs/2609.15727 · HTML: https://mlsanity.com/paper/2609.15727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://mlsanity.com/paper/2502.01506/) (2025)
- [BASES: Large-scale Web Search User Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2402.17505/) (2024)
- [SurrealDriver: Designing LLM-powered Generative Driver Agent Framework based on Human Drivers' Driving-thinking Data](https://mlsanity.com/paper/2309.13193/) (2023)
- [Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces](https://mlsanity.com/paper/2604.08362/) (2026)
- [Reinforcement Learning for Personalized Dialogue Management](https://mlsanity.com/paper/1908.00286/) (2019)
- [RecPS: Privacy Risk Scoring for Recommender Systems](https://mlsanity.com/paper/2507.18365/) (2025)
- [Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation](https://mlsanity.com/paper/2602.16990/) (2026)
- [LLM-Based User Personas for Recommendations at Scale](https://mlsanity.com/paper/2606.12198/) (2026)
- [ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors](https://mlsanity.com/paper/2608.01204/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as user simulators, yet it remains unclear whether their predictions faithfully reproduce the evolving decisions of individual users. We investigate this question in a controlled longitudinal paper-trading study with 80 participants, where user interactions, simulated transactions, virtual portfolio states, and point-in-time market information are aligned under a rolling next-day prediction protocol. We evaluate behavioral fidelity hierarchically, from trade occurrence to action structure, asset selection, and downstream portfolio consequences. Across 1,239 aligned user-days, no evaluated LLM reliably outperforms a simple recent-activity persistence baseline for predicting whether a user trades. Fidelity further deteriorates at finer levels: models struggle to recover buy--sell structure and traded assets, and similar activity-level predictions can lead to substantially different portfolio trajectories. Controlled evidence ablations show that recent trading history strongly governs activity prediction, whereas asset selection is substantially more sensitive to the available evidence. An observational analysis further finds that intensified ticker-specific research predicts imminent trading, but diagnostic tests do not support a causal interpretation. These findings suggest that current LLMs capture useful short-term behavioral regularities without yet recovering a stable individual decision mechanism.