Parshin Shojaee

DecAEvolve: Decompose, Adapt, and Evolve, or Three Pillars of Effective LLM-based Scientific Equation Discovery

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers

SurfaceBench: Can Self-Evolving LLMs Find the Equations of 3D Scientific Surfaces?

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity