Hubble: An LLM-Driven Agentic Framework for Safe and Automated Alpha Factor Discovery

Computer Science > Artificial Intelligence [Submitted on 9 Mar 2026] Hubble: An LLM-Driven Agentic Framework for Safe and Automated Alpha Factor Discovery Runze Shi, Shengyu Yan, Yuecheng Cai, Chengxi Lv Discovering predictive alpha factors in quantitative finance remains a formidable challenge due to the vast combinatorial search space and inherently low signal-to-noise ratios in financial data. Existing automated methods, particularly genetic programming, often produce complex, uninterpretable formulas prone to overfitting. We introduce Hubble, a closed-loop factor mining framework that leverages Large Language Models (LLMs) as intelligent search heuristics, constrained by a domain-specific operator language and an Abstract Syntax Tree (AST)-based execution sandbox. The framework evaluates candidate factors through a rigorous statistical pipeline encompassing cross-sectional Rank Information Coefficient (RankIC), annualized Information Ratio, and portfolio turnover. An evolutionary feedback mechanism returns top-performing factors and structured error diagnostics to the LLM, enabling iterative refinement across multiple generation rounds. In experiments conducted on a panel of 30 U.S. equities over 752 trading days, the system evaluated 181 syntactically valid factors from 122 unique candidates across three rounds, achieving a peak composite score of 0.827 with 100% computational stability. Our results demonstrate that combining LLM-driven generation with deterministic safety constraints yields an effective, interpretable, and reproducible approach to automated factor discovery. Subjects: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) Cite as: arXiv:2604.09601 [cs.AI]   (or arXiv:2604.09601v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.09601 Focus to learn more Submission history From: Shengyu Yan [view email] [v1] Mon, 9 Mar 2026 05:21:00 UTC (4,062 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)