mlsanityData to 14 Oct 2026

FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining

arXiv 2610.06947 ↗First posted 3 Oct 2026q-fin.PM cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents. Yet it remains unclear whether advances across these paradigms yield more generalizable, distinct, and economically useful financial signals. We introduce FactorBench, a portfolio-aware benchmark comparing roughly five thousand mined factors from nine automated mining methods across five equity markets. A shared data and evaluation contract supports both symbolic expressions and executable Python factors, connecting heterogeneous discovery algorithms to common signal combination and portfolio construction procedures. FactorBench traces the outputs of mining systems across three levels: factor validity, temporal generalization, and predictiveness beyond measured risk and style exposures; within- and across-method pool distinctness, including similarity to the benchmark Alpha101; and composite-signal quality and after-cost long-only and long--short portfolio performance. After systematically assessing whether advances in factor mining translate into signal quality and portfolio performance, FactorBench finds that no paradigm consistently dominates.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 3 Oct 2026.

Builds on

14 of 26 references.

References · 14

  1. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  2. 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 141
  3. 2020Qlib: An AI-oriented Quantitative Investment Platformcited by 81
  4. 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimizationcited by 43
  5. 2025AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decaycited by 42
  6. 2023Generating Synergistic Formulaic Alpha Collections via Reinforcement Learningcited by 39
  7. 2024AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factorscited by 27
  8. 2026QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Miningcited by 16
  9. 2025Cognitive Alpha Mining via LLM-Driven Code-Based Evolutioncited by 15
  10. 2025AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Miningcited by 11
  11. 2026From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Marketscited by 11
  12. 2026Alpha Discovery via Grammar-Guided Learning and Searchcited by 3
2 more
  1. 2025QuantBench: Benchmarking AI Methods for Quantitative Investmentcited by 2
  2. 2026AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining
  2. 2026AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery
  3. 2026FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical Validation
  4. 2026AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning
  5. 2025Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
  6. 2026From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
  7. 2026Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery
  8. 2025Deep Reinforcement Learning in Factor Investment