Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Representing Time Series as Structured Programs for LLM Reasoning

About

Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modality, raising a fundamental question: how should time series be represented so that LLMs can reason about them effectively? Existing work typically serializes raw numerical sequences or fine-tunes pre-trained LLMs on time-series data. These approaches place the burden of extracting temporal structure directly on the LLM, creating a modality mismatch that often degrades performance on long sequences and introduces substantial computational overhead. In this work, we introduce Time-Series-to-Structured-Program representation (T2SP), a deterministic, training-free method that represents a time series as a structured symbolic program. T2SP decomposes time series into trends, periods, and salient events, expressing them in a program-friendly format aligned with the textual and code-like modalities on which LLMs are natively trained. By shifting temporal-structure extraction from the model to the representation itself, T2SP enables off-the-shelf LLMs to leverage their existing reasoning capabilities for time-series understanding. We evaluate T2SP on three reasoning tasks -- editing, captioning, and question answering -- where it consistently improves performance, reduces reasoning time, and lowers failure rates compared with raw-string representations. Our results demonstrate that T2SP provides an effective interface between time series and LLMs.

Jaeho Kim, Changhun Oh, Seokhyun Lee, Irina Rish, Changhee Lee• 2026

Related benchmarks

TaskDatasetResultRank
Time Series ReasoningETI
Accuracy95
36
Time Series ReasoningTSQA
Accuracy86.7
36
Time Series ReasoningTRQA
Accuracy81.5
36
Caption-based ClassificationWafer
Accuracy89.5
15
Caption-based ClassificationECG200
Accuracy73
15
Time Series EditingTSEdit
Trend Fidelity97.6
15
Time Series EditingETTh1
Fidelity (Win Rate)91.4
6
Showing 7 of 7 rows

Other info

Follow for update