SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

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 t

Read original source ↗ Open in workspace

recordType

paper

region

Global