Search papers, labs, and topics across Lattice.
This paper introduces XAlpha, a memory-driven AI Quant Researcher designed to enhance the alpha discovery process in financial markets by integrating a multi-source research memory system. By closing the hypothesis-to-code validation loop and leveraging accumulated feedback, XAlpha transforms traditional isolated factor generation into a continuous, closed-loop research process. Experiments demonstrate that XAlpha outperforms existing methods in alpha discovery performance on the CSI300 index, highlighting its effectiveness in navigating the complexities of financial data.
XAlpha revolutionizes alpha discovery by turning it into a continuous learning process that adapts and evolves based on real-time feedback.
Financial markets are noisy, non-stationary, and high-dimensional, making it difficult to discover predictive and robust trading signals. Alpha discovery has evolved from manual factor design to machine learning, evolutionary search, and recent LLM-based frameworks, improving the efficiency of factor generation, search, and evaluation. However, existing methods still mostly automate isolated steps, rather than functioning as end-to-end quant researchers that can absorb external knowledge, close the hypothesis-to-code validation loop, and learn from accumulated discovery feedback. To fill this gap, we introduce XAlpha, a memory-driven AI Quant Researcher for continuous hypothesis-to-code alpha discovery. XAlpha maintains a multi-source research memory system that integrates report-grounded financial knowledge with discovery feedback from prior generations and research cycles. Guided by this memory system, a Macro Brain plans research themes and selects suitable Archetypes; a Micro Brain transforms the planned hypothesis pool into executable factor code and verifies ex-ante tri-alignment among the hypothesis idea, code logic, and financial plausibility; and a Cross Brain consolidates empirical outcomes into generation-level feedback, cycle-level summaries, and archetype-level research cues for future exploration. In this way, XAlpha turns alpha mining from isolated factor generation into a closed-loop research process that continuously reads, hypothesizes, implements, validates, reflects, and evolves. Experiments on CSI300 show that XAlpha achieves stronger overall alpha discovery performance than representative baselines.
