Tag
AlphaDiverse is a framework for automating alpha factor mining in quantitative research using post-trained local agents to ensure diverse exploration and maintain data confidentiality.
This paper proposes a governed self-evolution framework for LLM agents in quantitative factor research, where a frozen statistical referee judges proposed factors to reduce false discoveries, while agents focus on proposal and instrumentation.
A comprehensive guide on applying loop engineering to quantitative research, presenting a framework where LLM agents iteratively perceive, reason, act, and observe to generate and test alpha factors, with full code implementation and comparison to single-shot prompting.
The article highlights Jane Street's contribution to pushing the frontiers of Deep Learning through quantitative research, emphasizing the respect good researchers have for such work.
In this Anthropic guest post, Prof. Matthew Schwartz describes BootLoops, an open-source toolkit of scientific software and protocols built with Claude to do exact calculations in quantitative science. By deliberately targeting "Claude-shaped" problems, the tools surfaced cross-domain connections to ecology, population genetics and other fields, which domain experts then helped steer toward scientifically meaningful questions.