New research demonstrates how large language models can reliably translate natural language instructions into executable option trading strategies, opening the door to more intuitive and automated financial tools.
![The ASDA framework builds a skill library iteratively-beginning with an initial compilation of student errors, then refining it through phases that prioritize both comprehensive coverage of unresolved issues [latex]Q^{\mathrm{gap}}[/latex] and the prevention of performance regressions [latex]Q^{-}[/latex], with each skill update rigorously validated against a defined correctness threshold before integration into the student’s learning prompt.](https://arxiv.org/html/2603.16112v1/x1.png)
A new framework automatically refines large language models’ financial reasoning skills by learning from their mistakes-without retraining or new data.
New research reveals that artificial intelligence agents consistently produce unreliable results due to subtle choices in how they measure success.
Researchers have developed a framework to automatically identify meaningful features within sequences of events, improving both performance and our understanding of the underlying data.
A new framework uses the power of large language models and evolutionary algorithms to automatically discover and refine predictive factors for building profitable investment strategies.
This review explores how combining historical market data with alternative sources like earnings call transcripts can refine algorithmic trading strategies for improved performance.
![Across diverse graph signal categories, classifiers demonstrate consistent improvements in [latex] F_1 [/latex]-score when leveraging information beyond transactional data alone, as evidenced by aggregated results trimmed for robustness across random seeds.](https://arxiv.org/html/2603.13998v1/x1.png)
A new study establishes a rigorous protocol for evaluating the impact of graph-derived features on tabular machine learning models, revealing consistent performance gains and critical insights into signal robustness.
A new analysis reveals the fundamental limitations of artificial intelligence in replicating the complex narrative structures and emotional resonance of human-authored fiction.
A new framework transforms raw transaction data into usable knowledge, empowering large language models to perform more insightful and reliable financial analysis.
A critical analysis reveals that current evaluation methods in time-series forecasting are often misleading, masking a lack of genuine progress and hindering the development of robust predictive models.