Metraipolis › archive › dc_012f8255d60c

Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning — arXiv:2610.04942

Source
arXiv
Original
https://arxiv.org/abs/2610.04942
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:54.383Z
SHA-256 of the archived text
fe52af6e615343c407b0e944dbf6f5d6d3328aae862718a0efb476025fae3713
Stable URL of this page
https://metraipolis.com/documento/dc_012f8255d60c

How to cite

Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning — arXiv:2610.04942 — arXiv, https://arxiv.org/abs/2610.04942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_012f8255d60c (Metraipolis archive dc_012f8255d60c, sha256 fe52af6e615343c407b0e944dbf6f5d6d3328aae862718a0efb476025fae3713)
BibTeX
@misc{dc012f8255d60c,
  title = {Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning — arXiv:2610.04942},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04942},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_012f8255d60c; sha256 fe52af6e615343c407b0e944dbf6f5d6d3328aae862718a0efb476025fae3713},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04942 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.535Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).