The Evolution of Alpha in Finance Harnessing Human Insight and LLM Agents
On the map: LLM agents and tool use → Financial trading and forecasting agents
Abstract (arXiv)
The pursuit of alpha returns that exceed market benchmarks has undergone a profound transformation, evolving from intuition-driven investing to autonomous, AI powered systems. This paper introduces a comprehensive five stage taxonomy that traces this progression across manual strategies, statistical models, classical machine learning, deep learning, and agentic architectures powered by large language models (LLMs). Unlike prior surveys focused narrowly on modeling techniques, this review adopts a system level lens, integrating advances in representation learning, multimodal data fusion, and tool augmented LLM agents. The strategic shift from static predictors to contextaware financial agents capable of real time reasoning, scenario simulation, and cross modal decision making is emphasized. Key challenges in interpretability, data fragility, governance, and regulatory compliance areas critical to production deployment are examined. The proposed taxonomy offers a unified framework for evaluating maturity, aligning infrastructure, and guiding the responsible development of next generation alpha systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 18 of its 64 references that are in the map. First posted on arXiv 20 May 2025.
Builds on
18 of 64 references.
References · 18
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
- 2022Survey of Hallucination in Natural Language Generationcited by 2,075
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
- 2023BloombergGPT: A Large Language Model for Financecited by 939
- 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
6 more
- 2016The Mythos of Model Interpretabilitycited by 721
- 2019AutoML: A Survey of the State-of-the-Artcited by 390
- 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
- 2021True Few-Shot Learning with Language Modelscited by 344
- 2018Temporal Relational Ranking for Stock Predictioncited by 102
- 2016On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Productscited by 52
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning
- 2024FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
- 2026Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
- 2025MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
- 2025MASFIN: A Multi-Agent System for Decomposed Financial Reasoning and Forecasting
- 2025Integrating Traditional Technical Analysis with AI: A Multi-Agent LLM-Based Approach to Stock Market Forecasting
- 2026Agentic Trading: When LLM Agents Meet Financial Markets
- 2025AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay