# Regime-Aware Portfolio Management via Retrieval-Augmented LLM-Guided Expert Switching

arXiv: https://arxiv.org/abs/2608.28252 · HTML: https://mlsanity.com/paper/2608.28252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

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

- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?](https://mlsanity.com/paper/2510.02209/) (2025)
- [Cryptocurrency Portfolio Management with Deep Reinforcement Learning](https://mlsanity.com/paper/1612.01277/) (2016)
- [LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management](https://mlsanity.com/paper/2501.00826/) (2025)
- [TradExpert: Revolutionizing Trading with Mixture of Expert LLMs](https://mlsanity.com/paper/2411.00782/) (2024)
- [Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.14194/) (2020)
- [LLM-Based Routing in Mixture of Experts: A Novel Framework for Trading](https://mlsanity.com/paper/2501.09636/) (2025)
- [RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Markets](https://mlsanity.com/paper/2510.14986/) (2025)
- [A Reinforcement Learning Based Encoder-Decoder Framework for Learning Stock Trading Rules](https://mlsanity.com/paper/2101.03867/) (2021)
- [Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders](https://mlsanity.com/paper/2011.14346/) (2020)

## Abstract (arXiv)

Financial markets are inherently non-stationary, making the effectiveness of individual portfolio-management strategies highly dependent on changing market conditions. This work proposes a retrieval-augmented expert-switching framework that dynamically selects portfolio management experts based on their historical performance under similar market situations. A dual-stream variational autoencoder represents asset-level and market-wide information, while a retrieval-based knowledge base stores historical situations and expert performance. During inference, an instruction-tuned LLM reasons over the retrieved evidence to identify the most appropriate expert rather than directly generating portfolio actions. We further establish a monotonicity property showing that adding a locally superior expert cannot degrade the switching mechanism's performance. Experiments across cryptocurrency, stock, and foreign-exchange markets show that the proposed selector achieves the highest cumulative return and Sharpe ratio among the evaluated selection strategies in all three markets. In the stock market, for example, cumulative return increases from 26% for the best fixed expert to 34%, while the Sharpe ratio improves from 0.74 to 0.96. Ablation results confirm the importance of both retrieval and LLM reasoning, while experiments with different expert-pool sizes demonstrate the value of complementary expertise. Overall, the findings support retrieval-grounded expert switching as an effective approach to adaptive portfolio management in non-stationary financial environments.