Alpha 挖掘（Alpha Mining）是系統化量化分析的基石，是一個識別與構建能夠預測未來收益之 Alpha 因子（超額收益因子）的嚴謹過程。長期以來，發現具有預測能力的 Alpha 因子一直是專業量化分析師與大型金融機構的核心任務。本文介紹了一種新型的、基於智慧體 AI（Agentic AI）驅動的 Alpha 挖掘流程。該流程實現了一個多智慧體系統，能夠將以自然語言表述的投資直覺（例如簡單的交易想法）轉化為嚴謹、可執行且可進行回測的 Alpha 因子。同時我們透過改編的科技接受模型（Technology Acceptance Model, TAM）設計以人為中心的實驗。共有 21 位來自不同背景的受試者參與評估，並從四個構面進行分析，包括知覺易用性（Perceived Ease of Use）、知覺有用性（Perceived Usefulness）以及使用態度（Attitude Toward Using）。本研究的主要貢獻包括：(1) 提出一個面向 Alpha 挖掘多代理實作架構；以及 (2) 建立一套基於 TAM 的人機互動評估框架。

Alpha Mining, the cornerstone of systematic quantitative analysis, is a rigorous process of identifying and formulating alphas that can forecast future returns. The discovery of predictive alphas has historically been the important task of expert quantitative analysts and large finan-cial institutions. This paper introduces a novel Agentic AI-empowered alpha mining pipeline that implements a multi-agent system capable of translating investment intuition (e.g., a simple trading idea) stated in a natural language into rigorous, executable, and back-testable alpha factors. Additionally, we conduct a human-centric experiment based on modified Technology Acceptance Model (TAM). A total of 21 participants from diverse background evaluate through four dimensions: Perceived Ease of Use, Perceived Usefulness and Attitude Toward Using. This work contributions includes alpha mining implemented with multi-agent architecture and a evaluation framework based on TAM.

Abdelnabi, S., Gomaa, A., Sivaprasad, S., Schönherr, L., & Fritz, M. (2024). Cooperation, competition, and maliciousness: Llm-stakeholders interactive negotiation. Advances in Neural Information Processing Systems, 37, 83548– 83599.
Agashe, S., Fan, Y., Reyna, A., & Wang, X. E. (2025, April). Llm-coordination: evaluating and analyzing multi-agent coordination abilities in large language models. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 8038– 8057).
Ahvanooey, M. T., Li, Q., Wu, M., & Wang, S. (2019). A survey of genetic programming and its applications. KSII Transactions on Internet and Information Systems, 13(4), 1765– 1794.
Chen, Y., Arkin, J., Zhang, Y., Roy, N., & Fan, C. (2024, May). Scalable multi-robot collaboration with large language models: Centralized or decentralized systems? In 2024 IEEE International Conference on Robotics and Automation (ICRA) (pp. 4311– 4317). IEEE.
Cheng, Y., Zhang, C., Zhang, Z., Meng, X., Hong, S., Li, W., Wang, Z., Wang, Z., Yin, F., Zhao, J., & He, X. (2024). Exploring large language model based intelligent agents: Definitions, methods, and prospects. arXiv preprint arXiv:2401.03428.
Cui, C., Wang, W., Zhang, M., Chen, G., Luo, Z., & Ooi, B. C. (2021). AlphaEvolve: A learning framework to discover novel alphas in quantitative investment. In Proceedings of the 2021 International Conference on Management of Data (pp. 2208– 2216). ACM.
Davis, F. D. (1993). User acceptance of information technology: system characteristics, user perceptions, and behavioral impacts. International Journal of Man-Machine Studies, 38(3), 475– 487.
Ding, Z., Liu, Z., Fang, Z., Su, K., Zhu, L., & Lu, Z. (2024). Multi-agent coordination via multilevel communication. Advances in Neural Information Processing Systems, 37, 118513–118539.
Elkamouchi, R., Daaif, A., & Elguemmat, K. (2024, April). Multi-Agents System in Healthcare: A Systematic Literature Review. In International Conference on Smart Applications and Data Analysis (pp. 200– 214). Springer Nature Switzerland.
Fama, E. F., & French, K. R. (1992). The cross-section of expected stock returns. The Journal of Finance, 47(2), 427– 465.
Ferrag, M. A., Tihanyi, N., & Debbah, M. (2025). From llm reasoning to autonomous ai agents: A comprehensive review. arXiv preprint arXiv:2504.19678.
Gulli, A., Nigam, L., Wiesinger, J., Vuskovic, V., Sigler, I., Nardini, I., Stroppa, N., Kartakis, S., Saribekyan, N., Nawalgaria, A., & Bount, A. (2025, February). Agents companion [White paper]. Kaggle. https://www.kaggle.com/whitepaper-agent-companion
He, J., Treude, C., & Lo, D. (2025). LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision, and the Road Ahead. ACM Transactions on Software Engineering and Methodology, 34(5), 1– 30.
Kakushadze, Z. (2016). 101 formulaic alphas. Wilmott, 2016(84), 72– 81.
Liu, J., Yu, C., Gao, J., Xie, Y., Liao, Q., Wu, Y., & Wang, Y. (2023). Llm -powered hierarchical language agent for real-time human-ai coordination. arXiv preprint arXiv:2312.15224.
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023, December). G-eval: NLG evaluation using gpt-4 with better human alignment. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 2511– 2522).
Patil, R. R. (2023). AI-infused algorithmic trading: Genetic algorithms and machine learning in high-frequency trading. International Journal for Multidisciplinary Research, 5(5), 1– 12.
Ren, W., Qin, Y., & Li, Y. (2024). Alpha Mining and Enhancing via Warm Start Genetic Programming for Quantitative Investment. arXiv preprint arXiv:2412.00896.
Shi, H., Song, W., Zhang, X., Shi, J., Luo, C., Ao, X., Arian, H., & Seco, L. A. (2025, April).
Alphaforge: A framework to mine and dynamically combine formulaic alpha factors. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 12, pp. 12524–12532).
Tang, Z., Chen, Z., Yang, J., Mai, J., Zheng, Y., Wang, K., Chen, J., & Lin, L. (2025, August). Alphaagent: Llm-driven alpha mining with regularized exploration to counteract alpha decay. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Vol. 2, pp. 2813– 2822).
Tulchinsky, I. (2019). Introduction to alpha design. In I. Tulchinsky (Ed.), Finding Alphas: A quantitative approach to building trading strategies (pp. 1– 6). John Wiley & Sons.
Wang, S., Yuan, H., Zhou, L., Ni, L. M., Shum, H. Y., & Guo, J. (2025, November). Alpha-gpt: Human-ai interactive alpha mining for quantitative investment. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (pp. 196– 206).
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D.(2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824– 24837.
Wu, Z., Peng, R., Zheng, S., Liu, Q., Han, X., Kwon, B. I., Onizuka, M., Tang, S., & Xiao, C. (2024, November). Shall we team up: Exploring spontaneous cooperation of competing llm agents. In Findings of the Association for Computational Linguistics: EMNLP 2024 (pp.5163– 5186).
Xiao, Y., Sun, E., Luo, D., & Wang, W. (2024). TradingAgents: Multi-agents LLM financial trading framework. arXiv preprint arXiv:2412.20138.
Yang, S., Xin, J., Ye, Q., & Xia, H. (2025). A co-evolutionary genetic programming framework for market-adaptive formulaic alpha generation. Available at SSRN 5614909.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. R., & Cao, Y. (2022, October). React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T., Cao, Y., & Narasimhan, K. (2023). Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36, 11809– 11822.
Yu, S., Xue, H., Ao, X., Pan, F., He, J., Tu, D., & He, Q. (2023, August). Generating synergistic formulaic alpha collections via reinforcement learning. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 5476– 5486).
Yuan, H., Wang, S., & Guo, J. (2024). Alpha-GPT 2.0: Human-in-the-Loop AI for quantitative investment. arXiv preprint arXiv:2402.09746.
Zhao, J., Zhang, C., Qin, M., & Yang, P. (2025). QuantFactor REINFORCE: mining steady formulaic alpha factors with variance-bounded REINFORCE. IEEE Transactions on Signal Processing.
Zhao, Z., Chen, K., Guo, D., Chai, W., Ye, T., Zhang, Y., & Wang, G. (2024). Hierarchical auto organizing system for open-ended multi-agent navigation. arXiv preprint arXiv:2403.08282.