TS-Agent: A Time Series Reasoning Agent with Iterative Statistical Insight Gathering
This addresses time series reasoning for AI applications, offering an incremental hybrid approach that mitigates common LLM failures.
The paper tackles the problem of LLMs struggling with time series reasoning due to hallucination and knowledge leakage by proposing TS-Agent, which delegates statistical extraction to analytical tools and uses LLMs for evidence gathering and synthesis, achieving performance comparable to SOTA LLMs on understanding benchmarks and significant improvements on reasoning tasks.
Large language models (LLMs) have shown strong abilities in reasoning and problem solving, but recent studies reveal that they still struggle with time series reasoning tasks, where outputs are often affected by hallucination or knowledge leakage. In this work we propose TS-Agent, a time series reasoning agent that leverages LLMs strictly for what they excel at, i.e., gathering evidence and synthesizing it into conclusions through step-by-step reasoning, while delegating the extraction of statistical and structural information to time series analytical tools. Instead of mapping time series into text tokens, images, or embeddings, our agent interacts with raw numeric sequences through atomic operators, records outputs in an explicit evidence log, and iteratively refines its reasoning under the guidance of a self-critic and a final quality gate. This design avoids multi-modal alignment training, preserves the native form of time series, ensures interpretability and verifiability, and mitigates knowledge leakage or hallucination. Empirically, we evaluate the agent on established benchmarks. Our experiments show that TS-Agent achieves performance comparable to state-of-the-art LLMs on understanding benchmarks, and delivers significant improvements on reasoning tasks, where existing models often rely on memorization and fail in zero-shot settings.