TS-Agent：通过迭代洞察获取理解并推理原始时间序列
TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
AI总结：
TS-Agent通过迭代洞察获取机制，在时间序列理解和推理任务中匹配或超越文本、视觉及时间序列语言模型基线，尤其在零样本设置下表现更优。
摘要：
大型语言模型（LLMs）在符号和组合推理方面表现强大，但在时间序列问答中面临挑战，因为数据通常转换为LLM兼容的模态，如序列文本、图像或压缩时间序列嵌入。此类转换导致表示瓶颈，通常需要跨模态对齐或微调，并可能加剧幻觉和知识泄露。为解决这些限制，我们提出了TS-Agent，一个基于代理的、工具导向的框架，将LLM严格用于迭代证据推理，同时将统计和结构提取委托给在原始序列上运行的时间序列分析工具。我们的框架通过证据驱动的代理过程解决时间序列任务：（1）在ReAct风格循环中交替进行思考、工具执行和观察；（2）在显式证据日志中记录中间结果，并通过自我完善批评者纠正推理轨迹；（3）强制执行最终答案验证步骤以防止幻觉和泄露。在四个涵盖时间序列理解和推理的基准测试中，TS-Agent在文本、视觉和时间序列语言模型基线中匹配或超越，尤其在推理任务中表现最佳，其中多模态LLM在零样本设置下容易出现幻觉和知识泄露。
英文摘要：
Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted images, or compressed time series embeddings. Such conversions impose representation bottlenecks, often require cross-modal alignment or finetuning, and can exacerbate hallucination and knowledge leakage. To address these limitations, we propose TS-Agent, an agentic, tool-grounded framework that uses LLMs strictly for iterative evidence-based reasoning, while delegating statistical and structural extraction to time series analytical tools operating on raw sequences. Our framework solves time series tasks through an evidence-driven agentic process: (1) it alternates between thinking, tool execution, and observation in a ReAct-style loop, (2) records intermediate results in an explicit evidence log and corrects the reasoning trace via a self-refinement critic, and (3) enforces a final answer-verification step to prevent hallucinations and leakage. Across four benchmarks spanning time series understanding and reasoning, TS-Agent matches or exceeds strong text-based, vision-based, and time-series language model baselines, with the largest gains on reasoning tasks where multimodal LLMs are prone to hallucination and knowledge leakage in zero-shot settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
