XALPHA: A Memory-Driven AI Quant Researcher for Hypothesis-to-Code Alpha Discovery

• URL: http://arxiv.org/abs/2607.08332v2
• Date: Mon, 13 Jul 2026 07:04:03 GMT
• Title: XALPHA: A Memory-Driven AI Quant Researcher for Hypothesis-to-Code Alpha Discovery
• Abstract summary: XAlpha is a memory-driven AI Quant Researcher for continuous hypothesis-to-code alpha discovery.<n>It integrates report-grounded financial knowledge with discovery feedback from prior generations and research cycles.<n>XAlpha turns alpha mining from isolated factor generation into a closed-loop research process.
• Score: 11.611093390158908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents [87.95001910627825]
  AlphaMemo is a self-evolving alpha mining agent with Structured Search-Process Memory.<n>It records reusable evidence about which edit motifs work or fail under specific parent-factor contexts.<n>Experiments on CSI 500 and S&P 500 show improved out-of-sample performance and fixed-budget discovery efficiency.
  arXiv  Detail & Related papers  (2026-05-26T15:48:09Z)
• Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft [70.0241202837925]
  We introduce SciCrafter, a Minecraft-based benchmark that operationalizes the discovery-to-application loop.<n>We evaluate frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold.<n>Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle.
  arXiv  Detail & Related papers  (2026-04-27T16:58:04Z)
• Can we automatize scientific discovery in the cognitive sciences? [20.166894780789725]
  We propose a paradigm shift toward a fully automated, in silico science of the mind.<n>This framework implements every stage of the discovery cycle using Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2026-03-22T00:15:58Z)
• AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution [11.490182876149062]
  We introduce AlphaPROBE, a framework that reframes alpha mining as the strategic navigation of a Directed Acyclic Graph (DAG)<n>By modeling factors as nodes and evolutionary links as edges, AlphaPROBE treats the factor pool as a dynamic, interconnected ecosystem.<n>Our results confirm that leveraging global evolutionary topology is essential for efficient and robust automated alpha discovery.
  arXiv  Detail & Related papers  (2026-02-12T13:14:58Z)
• HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery [50.8841471967624]
  HiSciBench is a hierarchical benchmark designed to evaluate foundation models across five levels that mirror the complete scientific workflow.<n>HiSciBench contains 8,735 carefully curated instances spanning six major scientific disciplines.
  arXiv  Detail & Related papers  (2025-12-28T12:08:05Z)
• ThetaEvolve: Test-time Learning on Open Problems [110.5756538358217]
  We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time.<n>We find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines.
  arXiv  Detail & Related papers  (2025-11-28T18:58:14Z)
• Cognitive Alpha Mining via LLM-Driven Code-Based Evolution [29.71597480304934]
  We introduce the Cognitive Alpha Mining Framework (CogAlpha), which combines code-level alpha representation with LLM-driven reasoning and evolutionary search.<n>Treating LLMs as adaptive cognitive agents, our framework iteratively refines, mutates, and recombines alpha candidates through prompts and financial feedback.<n>Experiments on A-share equities demonstrate that CogAlpha consistently discovers alphas with superior predictive accuracy, robustness, and generalization over existing methods.
  arXiv  Detail & Related papers  (2025-11-24T07:45:59Z)
• Open-ended Scientific Discovery via Bayesian Surprise [63.26412847240136]
  AutoDS is a method for open-ended scientific discovery that instead drives scientific exploration using Bayesian surprise.<n>We evaluate AutoDS in the setting of data-driven discovery across 21 real-world datasets spanning domains such as biology, economics, finance, and behavioral science.
  arXiv  Detail & Related papers  (2025-06-30T22:53:59Z)
• AlphaEvolve: A coding agent for scientific and algorithmic discovery [63.13852052551106]
  We present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs.<n>AlphaEvolve orchestrates an autonomous pipeline of LLMs, whose task is to improve an algorithm by making direct changes to the code.<n>We demonstrate the broad applicability of this approach by applying it to a number of important computational problems.
  arXiv  Detail & Related papers  (2025-06-16T06:37:18Z)
• TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence [62.21106561772784]
  We introduce Temporal-aware Hierarchical Cognitive Reinforcement Learning (TimeHC-RL) for enhancing Large Language Models' social intelligence.<n> Experimental results reveal the superiority of our proposed TimeHC-RL method compared to the widely adopted System 2 RL method.<n>It gives the 7B backbone model wings, enabling it to rival the performance of advanced models like DeepSeek-R1 and OpenAI-O3.
  arXiv  Detail & Related papers  (2025-05-30T12:01:06Z)
• Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles [0.0]
  We present Sparks, a multi-modal multi-agent AI model that executes the entire discovery cycle.<n>Sparks can independently conduct rigorous scientific inquiry and identify previously unknown scientific principles.
  arXiv  Detail & Related papers  (2025-04-26T20:43:28Z)
• $\text{Alpha}^2$: Discovering Logical Formulaic Alphas using Deep Reinforcement Learning [28.491587815128575]
  We propose a novel framework for alpha discovery using deep reinforcement learning (DRL) A search algorithm guided by DRL navigates through the search space based on value estimates for potential alpha outcomes. Empirical experiments on real-world stock markets demonstrates $textAlpha2$'s capability to identify a diverse set of logical and effective alphas.
  arXiv  Detail & Related papers  (2024-06-24T10:21:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.