Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITs

By Zheng Li

Published 2026-01-22

Everscope rating

1556

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: LLM-Based Multi-Agent Investment System with SFT and GSPO Fine-Tuning. Problem types: Time Series Forecasting, Portfolio Optimization, Risk Management, Algorithmic Execution, Natural Language Processing, Reinforcement Learning, Transfer Learning.

arXiv:2602.00082 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.