Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITs
This addresses the problem of enhancing risk-adjusted returns for investors in the Chinese Public REITs market, though it is incremental as it applies existing LLM and multi-agent techniques to a specific financial domain.
The study tackled low-volatility Chinese Public REITs trading by proposing an LLM-driven multi-agent system with analytical, prediction, and decision agents, achieving significant outperformance over a buy-and-hold benchmark in backtests from October 2024 to October 2025 in terms of cumulative return, Sharpe ratio, and maximum drawdown.
This study addresses the low-volatility Chinese Public Real Estate Investment Trusts (REITs) market, proposing a large language model (LLM)-driven trading framework based on multi-agent collaboration. The system constructs four types of analytical agents-announcement, event, price momentum, and market-each conducting analysis from different dimensions; then the prediction agent integrates these multi-source signals to output directional probability distributions across multiple time horizons, then the decision agent generates discrete position adjustment signals based on the prediction results and risk control constraints, thereby forming a closed loop of analysis-prediction-decision-execution. This study further compares two prediction model pathways: for the prediction agent, directly calling the general-purpose large model DeepSeek-R1 versus using a specialized small model Qwen3-8B fine-tuned via supervised fine-tuning and reinforcement learning alignment. In the backtest from October 2024 to October 2025, both agent-based strategies significantly outperformed the buy-and-hold benchmark in terms of cumulative return, Sharpe ratio, and maximum drawdown. The results indicate that the multi-agent framework can effectively enhance the risk-adjusted return of REITs trading, and the fine-tuned small model performs close to or even better than the general-purpose large model in some scenarios.