The field of quantitative research and optimization is witnessing a significant shift with the integration of large language models (LLMs). Recent developments indicate a strong focus on leveraging LLMs to automate tasks such as alpha mining, digital twin planning, and optimization problem-solving. These models are being fine-tuned for specialized applications, including quantitative finance and telecommunications, demonstrating their potential to improve efficiency and accuracy in complex tasks. Noteworthy papers in this area include Chain-of-Alpha, which proposes a novel LLM-based framework for automated alpha mining, and X-evolve, which introduces a paradigm-shifting method for evolving solution spaces powered by LLMs. Additionally, MiGrATe and NEFMind showcase the effectiveness of LLMs in adaptation at test-time and parameter-efficient fine-tuning for telecom APIs automation, respectively. These advancements highlight the innovative applications of LLMs in driving progress in quantitative research and optimization.
Large Language Models in Quantitative Research and Optimization
Sources
Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading
LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning
Technical Report: Full-Stack Fine-Tuning for the Q Programming Language
Enhancing Decision Space Diversity in Multi-Objective Evolutionary Optimization for the Diet Problem
\(X\)-evolve: Solution space evolution powered by large language models
Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolution
MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation
A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions