发表机构
Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时间序列问答中现有方法过拟合特定数据集、难以泛化的问题，提出TSHarness智能体框架，通过解耦数值感知与上下文推理，实现跨数据集零样本问答。
AI 中文摘要
时间序列问答（TSQA）要求将语言查询和多样化的答案格式与复杂的数值观测相结合。然而，现有方法严重过拟合于特定数据集，当输入序列、问题上下文和答案需求同时变化时，难以泛化。为应对这一挑战，我们提出了TSHarness，一个智能体框架，建立了跨数据集零样本TSQA的解耦工作流。其核心在于，TSHarness通过结构化的时间序列感知状态（TPS）分而治之地处理数值感知和上下文推理。在可复用的分析知识记忆引导下，学习到的工具选择器自适应地调用数值工具，将显著的统计和时间特征提取到TPS中。随后，回答智能体对TPS进行语义推理以生成目标输出，当证据不足时，通过反馈循环触发迭代式重新感知。通过将数值特征提取与问题特定推理分离，TSHarness消除了对目标侧训练或答案反馈的需求，为零样本TSQA提供了可泛化、成本高效的基座。
英文摘要
Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily overfit to specific datasets and struggle to generalize when input series, question contexts, and answer requirements shift simultaneously. To address this challenge, we propose TSHarness, an agentic framework that establishes a decoupled workflow for cross-dataset zero-shot TSQA. At its core, TSHarness divides and conquers numerical perception and contextual reasoning via a structured Time-Series Perception State (TPS). Guided by a reusable memory of analytical knowledge, a learned Tool Selector adaptively invokes numerical tools to extract salient statistical and temporal features into the TPS. The answering agent then performs semantic reasoning over the TPS to generate target outputs, triggering iterative re-perception through the feedback loop when evidence is deemed insufficient. By separating numerical feature extraction from question-specific reasoning, TSHarness eliminates the need for target-side training or answer feedback, providing a generalizable, cost-efficient foundation for zero-shot TSQA.
