@inproceedings{liu-etal-2026-large-language,
    title = "Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?",
    author = "Liu, Zewen  and
      Ni, Juntong  and
      Tang, Xianfeng  and
      Lau, Max SY  and
      He, Qi  and
      Yin, Wenpeng  and
      Jin, Wei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1756/",
    pages = "35201--35226",
    ISBN = "979-8-89176-395-1",
    abstract = "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. 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."
}