Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?
This work addresses the challenge of automated scientific discovery for researchers and AI practitioners, but it is incremental as it builds on existing methods by integrating LLMs with genetic programming.
The paper tackled the problem of evaluating whether large language models can infer interpretable symbolic structures from time series data, and introduced SymbolBench, a benchmark for tasks like symbolic regression and causal discovery, showing that combining LLMs with genetic programming improves performance but reveals limitations in current models.
Uncovering hidden symbolic laws from time series data, as an aspiration dating back to Kepler's discovery of planetary motion, remains a core challenge in scientific discovery and artificial intelligence. While Large Language Models show promise in structured reasoning tasks, their ability to infer interpretable, context-aligned symbolic structures from time series data is still underexplored. To systematically evaluate this capability, we introduce SymbolBench, a comprehensive benchmark designed to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery. Unlike prior efforts limited to simple algebraic equations, SymbolBench spans a diverse set of symbolic forms with varying complexity. We further propose a unified framework that integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system, where LLMs act both as predictors and evaluators. Our empirical results reveal key strengths and limitations of current models, highlighting the importance of combining domain knowledge, context alignment, and reasoning structure to improve LLMs in automated scientific discovery.