arXiv preprint arXiv:2607.08332, 2026
Financial markets are noisy, non-stationary, and high-dimensional, making it difficult to discover predictive and robust trading signals. Alpha discovery has evolved from manual factor design to machine learning, evolutionary search, and recent LLM-based frameworks, improving the efficiency of factor generation, search, and evaluation.
arXiv preprint arXiv:2607.03935, 2026
Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-learning framework in which a single model can generate task solutions or edit selected harness components in a multi-turn action space.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
Discovering effective predictive signals, or “alphas,” from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despite progress in deep learning, genetic programming, and, more recently, large language model (LLM)–based factor generation, existing approaches still explore only a narrow region of the vast alpha search space.
Findings of the Association for Computational Linguistics: ACL 2026, 2026
Large Language Models (LLMs) are increasingly applied to alpha mining in quantitative finance, marking a shift from generating simple symbolic formulas to producing executable, code-based strategies. While code generation offers greater expressiveness, it introduces critical risks absent in symbolic approaches, including temporal causality violations (look-ahead bias) and stateful logic bugs.
Nature Biomedical Engineering, 2026
Large language models (LLMs), such as ChatGPT, have substantially helped in understanding human inquiries and generating textual content with human-level fluency. However, directly using LLMs in healthcare applications faces several problems.
arXiv preprint arXiv:2604.24372, 2026
Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when natural-language reasoning is used through heuristic descriptions or reflection, it typically remains transient mutation context or unstructured memory, rather than organized as persistent population-level state over strategic directions.
arXiv preprint arXiv:2512.21120, 2025
Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or ambiguous information. However, existing LLM-focused clarification benchmarks primarily assume single-turn interactions or cooperative users, limiting their ability to evaluate clarification behavior in realistic settings.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
Individual Large Language Models (LLMs) have demonstrated significant capabilities across various domains, such as healthcare and law. Recent studies also show that coordinated multi-agent systems exhibit enhanced decision-making and reasoning abilities through collaboration.
European Conference on Computer Vision (ECCV 2024), 2024
Recent progress in visual generative models enables the generation of high-quality images. To prevent the misuse of generated images, it is important to identify the origin model that generates them.
International Conference on Learning Representations (ICLR 2024), 2024
Different from traditional task-specific vision models, recent large VLMs can readily adapt to different vision tasks by simply using different textual instructions, i.e., prompts. However, a well-known concern about traditional task-specific vision models is that they can be misled by imperceptible adversarial perturbations.
International Conference on Machine Learning (ICML 2023), 2023
The goal of automated feature generation is to liberate machine learning experts from the laborious task of manual feature generation, which is crucial for improving the learning performance of tabular data. The major challenge in automated feature generation is to efficiently and accurately identify effective features from a vast pool of candidate features.
