[2610.14959] AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery
View a PDF of the paper titled AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery, by Jie Huang and 8 other authors
View PDF
HTML (experimental)
Abstract:Formulaic alpha mining seeks to discover executable expressions that capture predictive market signals in a vast, noisy search space. Recent LLM-based approaches use prompting, iterative search, or seed-factor evolution, leaving direct factor construction through policy learning less explored. To address this, we introduce AlphaRLM, a reinforcement-learning framework that trains LLMs to construct executable symbolic factors from financial literature without input factor expressions. AlphaRLM incorporates Literature-Guided Operator Assembly (LEGO), which conditions factor construction on literature-derived ideas and executable operators, providing semantic priors for exploration. It further aligns the generation policy with market feedback through executable-validity and grouped-return-separation rewards that capture non-monotonic structures across factor quantiles. Extensive experiments on CSI 300, CSI 1000, and S&P 500 show that AlphaRLM outperforms strong factor-mining and LLM-based baselines in annualized excess return. Notably, the 8B model achieves strong cross-market performance, highlighting the promise of literature-conditioned, market-aligned factor generation.
Submission history
From: Jie Huang [view email]
[v1]
Sat, 10 Oct 2026 14:32:10 UTC (2,914 KB)
[v2]
Wed, 14 Oct 2026 12:33:55 UTC (2,914 KB)
[v3]
Thu, 15 Oct 2026 03:53:15 UTC (2,914 KB)
![]()

No Comments