q-fin.GN papers | Gist.Science

This collection explores the cutting edge of Q-Fin — Gn, where advanced quantum computing principles intersect with financial modeling and game theory. These emerging studies investigate how quantum algorithms can solve complex economic problems and optimize strategic interactions far beyond the reach of classical computers, offering a glimpse into a future where financial markets operate with unprecedented speed and precision.

Every new preprint in this category originates from arXiv, the premier repository for physics and computer science research. At Gist.Science, we process each submission to provide both accessible plain-language explanations and detailed technical summaries, ensuring these breakthroughs are understandable to everyone from industry experts to curious students. Below are the latest papers in this rapidly evolving field, curated to keep you ahead of the curve.

💰 quantitative finance

AI Patents in the United States and China: Measurement, Organization, and Knowledge Flows

This paper introduces a high-precision AI patent classifier to reveal that while the United States and China exhibit converging AI patenting growth and market value premiums, they differ significantly in organizational structures—with the U.S. dominated by large private firms and China by diverse institutions—and remain technologically interdependent through cross-border knowledge flows.

Hanming Fang, Xian Gu, Hanyin Yan, Wu Zhu2026-04-14

💰 quantitative finance

Utilizing Pre-trained and Large Language Models for 10-K Items Segmentation

This study introduces and evaluates two advanced methods, BERT4ItemSeg and GPT4ItemSeg, for segmenting items in 10-K reports, demonstrating that the hierarchical BERT-based model achieves superior accuracy while the LLM-based approach offers greater adaptability to regulatory changes.

Hsin-Min Lu, Yu-Tai Chien, Huan-Hsun Yen, Yen-Hsiu Chen2026-04-09

💰 quantitative finance

Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorithmic Herding, and Cognitive Dependency in Financial Markets

This paper develops a unified model demonstrating that AI adoption in financial markets creates superlinear systemic risk through mutually reinforcing channels of performative prediction, algorithmic herding, and cognitive dependency, leading to convex fragility, potential algorithmic monocultures, and empirically validated tail-loss amplification of 18–54%.

Shuchen Meng, Xupeng Chen2026-04-07

💰 quantitative finance

Debiasing LLMs by Fine-tuning

This paper proposes a low-cost, generalizable method for debiasing large language models by using Low-Rank Adaptation (LoRA) to fine-tune them on rational benchmark forecasts, which effectively mitigates systematic extrapolation bias in both controlled experiments and stock return predictions.

Zhenyu Gao, Wenxi Jiang, Yutong Yan2026-04-06

💰 quantitative finance

The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management

This paper presents an agentic AI framework for institutional asset management where approximately 50 specialized agents collaboratively generate, construct, and critique portfolios under the governance of an Investment Policy Statement, while a meta-agent autonomously rewrites their code and prompts to continuously improve performance based on realized returns.

Andrew Ang, Nazym Azimbayev, Andrey Kim2026-04-03

💰 quantitative finance

Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex Trading

This paper proposes a modular reinforcement learning framework for Forex trading that integrates a friction-aware execution engine, a decomposable 11-component reward architecture, and a constrained 10-action interface to overcome prior limitations in simulator realism and reward design, demonstrating that while expanded action spaces increase returns, they also heighten turnover and require careful reward tuning to optimize the return-drawdown trade-off.

Nabeel Ahmad Saidd2026-04-02

💰 quantitative finance

ESG Integration into Corporate Strategy Value Realization

This paper argues that since China's 2020 "dual-carbon" strategy, ESG integration has evolved from a policy directive into a societal consensus, necessitating a fundamental corporate shift from short-term financial focus to long-term, non-financial value creation through the deep embedding of ESG principles into core strategy and operations.

Li Xiao2026-03-31

💰 quantitative finance

Cryptocurrency as an Investable Asset Class: Coming of Age

This paper organizes empirical regularities of cryptocurrencies into seven stylized facts, demonstrating that while they share risk-adjusted performance and factor structures with traditional markets, their distinct characteristics like frequent jumps and blockchain-driven pricing confirm their emergence as a viable investable asset class.

Nicola Borri, Yukun Liu, Aleh Tsyvinski, Xi Wu2026-03-24

💰 quantitative finance

A Controlled Comparison of Deep Learning Architectures for Multi-Horizon Financial Forecasting: Evidence from 918 Experiments

Through a rigorous controlled comparison of 918 experiments across nine deep learning architectures, this study identifies ModernTCN as the superior model for multi-horizon financial forecasting, demonstrating that architectural inductive bias significantly outweighs hyperparameter tuning and seed randomness while revealing that current MSE-trained models lack directional skill at hourly resolutions.

Nabeel Ahmad Saidd2026-03-19

💰 quantitative finance

LR-Robot: A Unified Supervised Intelligent Framework for Real-Time Systematic Literature Reviews with Large Language Models

LR-Robot is a novel, unified supervised framework that integrates large language models with human-in-the-loop oversight and retrieval-augmented generation to automate systematic literature reviews, enabling efficient, contextually accurate, and multidimensional analysis of research trends and relationships.

Wei Wei, Jin Zheng, Zining Wang2026-03-19

← Previous Next →