IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2510.15949.html
   My bibliography  Save this paper

ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination

Author

Listed:
  • Charidimos Papadakis
  • Angeliki Dimitriou
  • Giorgos Filandrianos
  • Maria Lymperaiou
  • Konstantinos Thomas
  • Giorgos Stamou

Abstract

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading with LLM AgentS), a unified multi-agent framework that integrates structured information from markets, news, and corporate fundamentals to support robust trading decisions. Within ATLAS, the central trading agent operates in an order-aware action space, ensuring that outputs correspond to executable market orders rather than abstract signals. The agent can incorporate feedback while trading using Adaptive-OPRO, a novel prompt-optimization technique that dynamically adapts the prompt by incorporating real-time, stochastic feedback, leading to increasing performance over time. Across regime-specific equity studies and multiple LLM families, Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains.

Suggested Citation

  • Charidimos Papadakis & Angeliki Dimitriou & Giorgos Filandrianos & Maria Lymperaiou & Konstantinos Thomas & Giorgos Stamou, 2025. "ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination," Papers 2510.15949, arXiv.org.
    • Handle: RePEc:arx:papers:2510.15949
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2510.15949
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Qianggang Ding & Haochen Shi & Jiadong Guo & Bang Liu, 2024. "TradExpert: Revolutionizing Trading with Mixture of Expert LLMs," Papers 2411.00782, arXiv.org, revised May 2025.
    2. Min-Yuh Day & Yirung Cheng & Paoyu Huang & Yensen Ni, 2023. "The profitability of Bollinger Bands trading bitcoin futures," Applied Economics Letters, Taylor & Francis Journals, vol. 30(11), pages 1437-1443, June.
    3. Jian Wang & Junseok Kim, 2018. "Predicting Stock Price Trend Using MACD Optimized by Historical Volatility," Mathematical Problems in Engineering, Hindawi, vol. 2018, pages 1-12, December.
    4. Yangyang Yu & Haohang Li & Zhi Chen & Yuechen Jiang & Yang Li & Denghui Zhang & Rong Liu & Jordan W. Suchow & Khaldoun Khashanah, 2023. "FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design," Papers 2311.13743, arXiv.org, revised Dec 2023.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Yuan Li & Bingqiao Luo & Qian Wang & Nuo Chen & Xu Liu & Bingsheng He, 2024. "A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading," Papers 2407.09546, arXiv.org.
    2. Yichen Luo & Yebo Feng & Jiahua Xu & Paolo Tasca & Yang Liu, 2025. "LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management," Papers 2501.00826, arXiv.org, revised Jan 2025.
    3. Yijia Xiao & Edward Sun & Tong Chen & Fang Wu & Di Luo & Wei Wang, 2025. "Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning," Papers 2509.11420, arXiv.org.
    4. Thi Thu Giang Nguyen & Robert Ślepaczuk, 2022. "The efficiency of various types of input layers of LSTM model in investment strategies on S&P500 index," Working Papers 2022-29, Faculty of Economic Sciences, University of Warsaw.
    5. Yensen Ni, 2024. "Navigating Energy and Financial Markets: A Review of Technical Analysis Used and Further Investigation from Various Perspectives," Energies, MDPI, vol. 17(12), pages 1-22, June.
    6. Tao Ren & Ruihan Zhou & Jinyang Jiang & Jiafeng Liang & Qinghao Wang & Yijie Peng, 2024. "RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search," Papers 2402.07080, arXiv.org, revised Feb 2024.
    7. Wentao Zhang & Lingxuan Zhao & Haochong Xia & Shuo Sun & Jiaze Sun & Molei Qin & Xinyi Li & Yuqing Zhao & Yilei Zhao & Xinyu Cai & Longtao Zheng & Xinrun Wang & Bo An, 2024. "A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist," Papers 2402.18485, arXiv.org, revised Jun 2024.
    8. Sukono & Dedi Rosadi & Di Asih I Maruddani & Riza Andrian Ibrahim & Muhamad Deni Johansyah, 2024. "Mechanisms of Stock Selection and Its Capital Weighing in the Portfolio Design Based on the MACD-K-Means-Mean-VaR Model," Mathematics, MDPI, vol. 12(2), pages 1-22, January.
    9. Yupeng Cao & Zhi Chen & Prashant Kumar & Qingyun Pei & Yangyang Yu & Haohang Li & Fabrizio Dimino & Lorenzo Ausiello & K. P. Subbalakshmi & Papa Momar Ndiaye, 2024. "RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data," Papers 2404.07452, arXiv.org, revised May 2025.
    10. Ramchandra Rimal & Binod Rimal & Hum Nath Bhandari & Nawa Raj Pokhrel & Keshab R. Dahal, 2025. "Real Estate Market Prediction Using Deep Learning Models," Annals of Data Science, Springer, vol. 12(4), pages 1113-1156, August.
    11. Hum Nath Bhandari & Nawa Raj Pokhrel & Ramchandra Rimal & Keshab R. Dahal & Binod Rimal, 2024. "Implementation of deep learning models in predicting ESG index volatility," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 10(1), pages 1-24, December.
    12. Mostapha Benhenda, 2025. "FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents," Papers 2502.07393, arXiv.org.
    13. Weixian Waylon Li & Hyeonjun Kim & Mihai Cucuringu & Tiejun Ma, 2025. "Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?," Papers 2505.07078, arXiv.org, revised Aug 2025.
    14. Xiangyu Li & Yawen Zeng & Xiaofen Xing & Jin Xu & Xiangmin Xu, 2025. "HedgeAgents: A Balanced-aware Multi-agent Financial Trading System," Papers 2502.13165, arXiv.org.
    15. Han Ding & Yinheng Li & Junhao Wang & Hang Chen, 2024. "Large Language Model Agent in Financial Trading: A Survey," Papers 2408.06361, arXiv.org.
    16. Srivastava, Varad, 2025. "EAGLE: A Multi-Agent Generative AI System for Personalized Banking Recommendation and Risk-Aware Financial Planning," OSF Preprints dwspv_v1, Center for Open Science.
    17. Traianos-Ioannis Theodorou & Alexandros Zamichos & Michalis Skoumperdis & Anna Kougioumtzidou & Kalliopi Tsolaki & Dimitris Papadopoulos & Thanasis Patsios & George Papanikolaou & Athanasios Konstanti, 2021. "An AI-Enabled Stock Prediction Platform Combining News and Social Sensing with Financial Statements," Future Internet, MDPI, vol. 13(6), pages 1-22, May.
    18. Lorette DANILO & Fayssal JAMHAMED & Franck MARTIN, 2024. "Optimized pairs-trading strategies in the cryptocurrencies market using genetic algorithms and cointegration," Economics Working Paper Archive (University of Rennes & University of Caen) 2024-11, Center for Research in Economics and Management (CREM), University of Rennes, University of Caen and CNRS.
    19. Chen & Jo-Hui & Hussain & Sabbor & Chen & Fu-Ying, 2023. "The Relationship between VIX and Technical Indicator: The Analysis of Shared-Frailty Model," Journal of Applied Finance & Banking, SCIENPRESS Ltd, vol. 13(3), pages 1-5.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2510.15949. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.