arXiv · arXiv · 2026
Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an agentic AI framework that replaces the traditional signal then execute paradigm with a fully autonomous deliberative loop in which multiple specialized Large Language Model agents r…
Ivan Letteri
arXiv · arXiv · 2026
Copy trading has become the dominant entry strategy in meme coin markets. However, due to the market's extremely illiquid and volatile nature, the strategy exposes an exploitable attack surface: adversaries deploy manipulative bots to front-run trades, conceal positions, and fabricate sentiment, systematically extracting value from naïve copiers at scale. Despite its prevalence, bot-driven manipulation remains largel…
Yichen Luo, Yebo Feng, Jiahua Xu, Yang Liu
arXiv · arXiv · 2026
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial decision is challenged by the market's stochastic nature: rewards are verifiable but inherently noisy, causing standard RL to degenerate into reward hacking. To address this, we propose…
Rui Sun, Yifan Sun, Sheng Xu, Li Zhao, Jing Li
arXiv · arXiv · 2025
Multi-hop reasoning over financial disclosures is often a retrieval problem before it becomes a reasoning or generation problem: relevant facts are dispersed across sections, filings, companies, and years, and LLMs often expend excessive tokens navigating noisy context. Without precise Knowledge Graph (KG)-guided selection of relevant context, even strong reasoning models either fail to answer or consume excessive to…
Abhinav Arun, Reetu Raj Harsh, Bhaskarjit Sarmah, Stefano Pasquali
arXiv · arXiv · 2025
Developing professional, structured reasoning on par with human financial analysts and traders remains a central challenge in AI for finance, where markets demand interpretability and trust. Traditional time-series models lack explainability, while LLMs face challenges in turning natural-language analysis into disciplined, executable trades. Although reasoning LLMs have advanced in step-by-step planning and verificat…
Yijia Xiao, Edward Sun, Tong Chen, Fang Wu, Di Luo
arXiv · arXiv · 2025
Financial decision-making presents unique challenges for language models, demanding temporal reasoning, adaptive risk assessment, and responsiveness to dynamic events. While large language models (LLMs) show strong general reasoning capabilities, they often fail to capture behavioral patterns central to human financial decisions-such as expert reliance under information asymmetry, loss-averse sensitivity, and feedbac…
Jiaxiang Chen, Mingxi Zou, Zhuo Wang, Qifan Wang, Dongning Sun
arXiv · arXiv · 2022
The efficient market hypothesis (EMH), based on rational expectations and market equilibrium, is the dominant perspective for modelling economic markets. However, the most notable critique of the EMH is the inability to model periods of out-of-equilibrium behaviour in the absence of any significant external news. When such dynamics emerge endogenously, the traditional economic frameworks provide no explanation for su…
Benjamin Patrick Evans, Mikhail Prokopenko
arXiv · arXiv · 2025
We consider state of the art applications of artificial intelligence (AI) in modelling human financial expectations and explore the potential of quantum logic to drive future advancements in this field. This analysis highlights the application of machine learning techniques, including reinforcement learning and deep neural networks, in financial statement analysis, algorithmic trading, portfolio management, and robo-…
Fabio Bagarello, Francesco Gargano, Polina Khrennikova
arXiv · arXiv · 2026
Large language models (LLMs) have shown strong performance across diverse financial tasks, yet portfolio management (PM) remains poorly benchmarked. Existing benchmarks exhibit two gaps: they are often equity-only and ignore cross-asset correlations; they fail to evaluate the complete PM decision pipeline. We introduce PortBench, a benchmark spanning six heterogeneous asset classes from 2015 to 2025. PortBench compri…
Yuxuan Zhao, Sijia Chen, Ningxin Su
arXiv · arXiv · 2025
Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the bread…
Yichen Luo, Yebo Feng, Jiahua Xu, Paolo Tasca, Yang Liu
arXiv · arXiv · 2023
In decentralized finance ("DeFi"), automated market makers (AMMs) enable traders to programmatically exchange one asset for another. Such trades are enabled by the assets deposited by liquidity providers (LPs). The goal of this paper is to characterize and interpret the optimal (i.e., profit-maximizing) strategy of a monopolist liquidity provider, as a function of that LP's beliefs about asset prices and trader behav…
Jason Milionis, Ciamac C. Moallemi, Tim Roughgarden
arXiv · arXiv · 2016
In this work we investigate tick-by-tick data provided by the TRTH database for several stocks on three different exchanges (Paris - Euronext, London and Frankfurt - Deutsche Börse) and on a 5-year span. We use a simple algorithm that helps the synchronization of the trades and quotes data sources, providing enhancements to the basic procedure that, depending on the time period and the exchange, are shown to be signi…
Ioane Muni Toke
arXiv · arXiv · 2026
Recent advances in large language models, tool-using agents, and financial machine learning are shifting financial automation from isolated prediction tasks to integrated decision systems that can perceive information, reason over objectives, and generate or execute actions. This paper develops an integrative framework for analysing agentic finance: financial market environments in which autonomous or semi-autonomous…
Hui Gong
arXiv · arXiv · 2026
This study introduces a benchmark framework for evaluating the financial decision-making capabilities of large language models (LLMs) through portfolio optimization problems with mathematically explicit solutions. Unlike existing financial benchmarks that emphasize language-processing tasks, the proposed framework directly tests optimization-based reasoning in investment contexts. A large set of multiple-choice quest…
Hanyong Cho, Jang Ho Kim
arXiv · arXiv · 2025
Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating L…
Haofei Yu, Fenghai Li, Jiaxuan You
arXiv · arXiv · 2025
This paper presents a realistic simulated stock market where large language models (LLMs) act as heterogeneous competing trading agents. The open-source framework incorporates a persistent order book with market and limit orders, partial fills, dividends, and equilibrium clearing alongside agents with varied strategies, information sets, and endowments. Agents submit standardized decisions using structured outputs an…
Alejandro Lopez-Lira