Language Model Guided Reinforcement Learning in Quantitative Trading ArXiv ID: 2508.02366 “View on arXiv” Authors: Adam Darmanin, Vince Vella Abstract Algorithmic trading requires short-term tactical decisions consistent with long-term financial objectives. Reinforcement Learning (RL) has been applied to such problems, but adoption is limited by myopic behaviour and opaque policies. Large Language Models (LLMs) offer complementary strategic reasoning and multi-modal signal interpretation when guided by well-structured prompts. This paper proposes a hybrid framework in which LLMs generate high-level trading strategies to guide RL agents. We evaluate (i) the economic rationale of LLM-generated strategies through expert review, and (ii) the performance of LLM-guided agents against unguided RL baselines using Sharpe Ratio (SR) and Maximum Drawdown (MDD). Empirical results indicate that LLM guidance improves both return and risk metrics relative to standard RL. ...

Neural Network-Based Algorithmic Trading Systems: Multi-Timeframe Analysis and High-Frequency Execution in Cryptocurrency Markets ArXiv ID: 2508.02356 “View on arXiv” Authors: Wěi Zhāng Abstract This paper explores neural network-based approaches for algorithmic trading in cryptocurrency markets. Our approach combines multi-timeframe trend analysis with high-frequency direction prediction networks, achieving positive risk-adjusted returns through statistical modeling and systematic market exploitation. The system integrates diverse data sources including market data, on-chain metrics, and orderbook dynamics, translating these into unified buy/sell pressure signals. We demonstrate how machine learning models can effectively capture cross-timeframe relationships, enabling sub-second trading decisions with statistical confidence. ...

SoK: Stablecoins for Digital Transformation – Design, Metrics, and Application with Real World Asset Tokenization as a Case Study ArXiv ID: 2508.02403 “View on arXiv” Authors: Luyao Zhang Abstract Stablecoins have become a foundational component of the digital asset ecosystem, with their market capitalization exceeding 230 billion USD as of May 2025. As fiat-referenced and programmable assets, stablecoins provide low-latency, globally interoperable infrastructure for payments, decentralized finance, DeFi, and tokenized commerce. Their accelerated adoption has prompted extensive regulatory engagement, exemplified by the European Union’s Markets in Crypto-assets Regulation, MiCA, the US Guiding and Establishing National Innovation for US Stablecoins Act, GENIUS Act, and Hong Kong’s Stablecoins Bill. Despite this momentum, academic research remains fragmented across economics, law, and computer science, lacking a unified framework for design, evaluation, and application. This study addresses that gap through a multi-method research design. First, it synthesizes cross-disciplinary literature to construct a taxonomy of stablecoin systems based on custodial structure, stabilization mechanism, and governance. Second, it develops a performance evaluation framework tailored to diverse stakeholder needs, supported by an open-source benchmarking pipeline to ensure transparency and reproducibility. Third, a case study on Real World Asset tokenization illustrates how stablecoins operate as programmable monetary infrastructure in cross-border digital systems. By integrating conceptual theory with empirical tools, the paper contributes: a unified taxonomy for stablecoin design; a stakeholder-oriented performance evaluation framework; an empirical case linking stablecoins to sectoral transformation; and reproducible methods and datasets to inform future research. These contributions support the development of trusted, inclusive, and transparent digital monetary infrastructure. ...

The Financial Connectome: A Brain-Inspired Framework for Modeling Latent Market Dynamics ArXiv ID: 2508.02012 “View on arXiv” Authors: Yuda Bi, Vince D Calhoun Abstract We propose the Financial Connectome, a new scientific discipline that models financial markets through the lens of brain functional architecture. Inspired by the foundational work of group independent component analysis (groupICA) in neuroscience, we reimagine markets not as collections of assets, but as high-dimensional dynamic systems composed of latent market modules. Treating stocks as functional nodes and their co-fluctuations as expressions of collective cognition, we introduce dynamic Market Network Connectivity (dMNC), the financial analogue of dynamic functional connectivity (dFNC). This biologically inspired framework reveals structurally persistent market subnetworks, captures regime shifts, and uncovers systemic early warning signals all without reliance on predictive labels. Our results suggest that markets, like brains, exhibit modular, self-organizing, and temporally evolving architectures. This work inaugurates the field of financial connectomics, a principled synthesis of systems neuroscience and quantitative finance aimed at uncovering the hidden logic of complex economies. ...

CTBench: Cryptocurrency Time Series Generation Benchmark ArXiv ID: 2508.02758 “View on arXiv” Authors: Yihao Ang, Qiang Wang, Qiang Huang, Yifan Bao, Xinyu Xi, Anthony K. H. Tung, Chen Jin, Zhiyong Huang Abstract Synthetic time series are essential tools for data augmentation, stress testing, and algorithmic prototyping in quantitative finance. However, in cryptocurrency markets, characterized by 24/7 trading, extreme volatility, and rapid regime shifts, existing Time Series Generation (TSG) methods and benchmarks often fall short, jeopardizing practical utility. Most prior work (1) targets non-financial or traditional financial domains, (2) focuses narrowly on classification and forecasting while neglecting crypto-specific complexities, and (3) lacks critical financial evaluations, particularly for trading applications. To address these gaps, we introduce \textsf{“CTBench”}, the first comprehensive TSG benchmark tailored for the cryptocurrency domain. \textsf{“CTBench”} curates an open-source dataset from 452 tokens and evaluates TSG models across 13 metrics spanning 5 key dimensions: forecasting accuracy, rank fidelity, trading performance, risk assessment, and computational efficiency. A key innovation is a dual-task evaluation framework: (1) the \emph{“Predictive Utility”} task measures how well synthetic data preserves temporal and cross-sectional patterns for forecasting, while (2) the \emph{“Statistical Arbitrage”} task assesses whether reconstructed series support mean-reverting signals for trading. We benchmark eight representative models from five methodological families over four distinct market regimes, uncovering trade-offs between statistical fidelity and real-world profitability. Notably, \textsf{“CTBench”} offers model ranking analysis and actionable guidance for selecting and deploying TSG models in crypto analytics and strategy development. ...

Hedging with memory: shallow and deep learning with signatures ArXiv ID: 2508.02759 “View on arXiv” Authors: Eduardo Abi Jaber, Louis-Amand Gérard Abstract We investigate the use of path signatures in a machine learning context for hedging exotic derivatives under non-Markovian stochastic volatility models. In a deep learning setting, we use signatures as features in feedforward neural networks and show that they outperform LSTMs in most cases, with orders of magnitude less training compute. In a shallow learning setting, we compare two regression approaches: the first directly learns the hedging strategy from the expected signature of the price process; the second models the dynamics of volatility using a signature volatility model, calibrated on the expected signature of the volatility. Solving the hedging problem in the calibrated signature volatility model yields more accurate and stable results across different payoffs and volatility dynamics. ...

Time-Varying Factor-Augmented Models for Volatility Forecasting ArXiv ID: 2508.01880 “View on arXiv” Authors: Duo Zhang, Jiayu Li, Junyi Mo, Elynn Chen Abstract Accurate volatility forecasts are vital in modern finance for risk management, portfolio allocation, and strategic decision-making. However, existing methods face key limitations. Fully multivariate models, while comprehensive, are computationally infeasible for realistic portfolios. Factor models, though efficient, primarily use static factor loadings, failing to capture evolving volatility co-movements when they are most critical. To address these limitations, we propose a novel, model-agnostic Factor-Augmented Volatility Forecast framework. Our approach employs a time-varying factor model to extract a compact set of dynamic, cross-sectional factors from realized volatilities with minimal computational cost. These factors are then integrated into both statistical and AI-based forecasting models, enabling a unified system that jointly models asset-specific dynamics and evolving market-wide co-movements. Our framework demonstrates strong performance across two prominent asset classes-large-cap U.S. technology equities and major cryptocurrencies-over both short-term (1-day) and medium-term (7-day) horizons. Using a suite of linear and non-linear AI-driven models, we consistently observe substantial improvements in predictive accuracy and economic value. Notably, a practical pairs-trading strategy built on our forecasts delivers superior risk-adjusted returns and profitability, particularly under adverse market conditions. ...

Tokenize Everything, But Can You Sell It? RWA Liquidity Challenges and the Road Ahead ArXiv ID: 2508.11651 “View on arXiv” Authors: Rischan Mafrur Abstract The tokenization of real-world assets (RWAs) promises to transform financial markets by enabling fractional ownership, global accessibility, and programmable settlement of traditionally illiquid assets such as real estate, private credit, and government bonds. While technical progress has been rapid, with over $25 billion in tokenized RWAs brought on-chain as of 2025, liquidity remains a critical bottleneck. This paper investigates the gap between tokenization and tradability, drawing on recent academic research and market data from platforms such as RWA.xyz. We document that most RWA tokens exhibit low trading volumes, long holding periods, and limited investor participation, despite their potential for 24/7 global markets. Through case studies of tokenized real estate, private credit, and tokenized treasury funds, we present empirical liquidity observations that reveal low transfer activity, limited active address counts, and minimal secondary trading for most tokenized asset classes. Next, we categorize the structural barriers to liquidity, including regulatory gating, custodial concentration, whitelisting, valuation opacity, and lack of decentralized trading venues. Finally, we propose actionable pathways to improve liquidity, ranging from hybrid market structures and collateral-based liquidity to transparency enhancements and compliance innovation. Our findings contribute to the growing discourse on digital asset market microstructure and highlight that realizing the liquidity potential of RWAs requires coordinated progress across legal, technical, and institutional domains. ...

CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration ArXiv ID: 2508.02738 “View on arXiv” Authors: Yumeng Shi, Zhongliang Yang, DiYang Lu, Yisi Wang, Yiting Zhou, Linna Zhou Abstract Corporate credit rating serves as a crucial intermediary service in the market economy, playing a key role in maintaining economic order. Existing credit rating models rely on financial metrics and deep learning. However, they often overlook insights from non-financial data, such as corporate annual reports. To address this, this paper introduces a corporate credit rating framework that integrates financial data with features extracted from annual reports using FinBERT, aiming to fully leverage the potential value of unstructured text data. In addition, we have developed a large-scale dataset, the Comprehensive Corporate Rating Dataset (CCRD), which combines both traditional financial data and textual data from annual reports. The experimental results show that the proposed method improves the accuracy of the rating predictions by 8-12%, significantly improving the effectiveness and reliability of corporate credit ratings. ...

From fair price to fair volatility: Towards an Efficiency-Consistent Definition of Financial Risk ArXiv ID: 2508.11649 “View on arXiv” Authors: Sergio Bianchi, Daniele Angelini, Massimiliano Frezza, Augusto Pianese Abstract Volatility, as a primary indicator of financial risk, forms the foundation of classical frameworks such as Markowitz’s Portfolio Theory and the Efficient Market Hypothesis (EMH). However, its conventional use rests on assumptions-most notably, the Markovian nature of price dynamics-that often fail to reflect key empirical characteristics of financial markets. Fractional stochastic volatility models expose these limitations by demonstrating that volatility alone is insufficient to capture the full structure of return dispersion. In this context, we propose pointwise regularity, measured via the Hurst-Holder exponent, as a complementary metric of financial risk. This measure quantifies local deviations from martingale behavior, enabling a more nuanced assessment of market inefficiencies and the mechanisms by which equilibrium is restored. By accounting not only for the magnitude but also for the nature of randomness, this framework bridges the conceptual divide between efficient market theory and behavioral finance. ...