Metraipolis › archive › dc_cbc92f8fac14
TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series — arXiv:2609.26389
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26389
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:47:11.816Z
- SHA-256 of the archived text
2db68a5263417b8a576f608010e11b5e8855e83fa6e312ea4e5ee89c724972c5- Stable URL of this page
https://metraipolis.com/documento/dc_cbc92f8fac14
How to cite
TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series — arXiv:2609.26389 — arXiv (en), https://arxiv.org/abs/2609.26389 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbc92f8fac14 (Metraipolis archive dc_cbc92f8fac14, sha256 2db68a5263417b8a576f608010e11b5e8855e83fa6e312ea4e5ee89c724972c5)
BibTeX
@misc{dccbc92f8fac14,
title = {TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series — arXiv:2609.26389},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26389},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbc92f8fac14; sha256 2db68a5263417b8a576f608010e11b5e8855e83fa6e312ea4e5ee89c724972c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26389. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inherently static. They either receive complete sequences for offline processing or alternate between streaming input and response generation, which prevents processing of new observations during interaction. We introduce a new regime, Time-Series Interaction: a model continuously perceives incoming time-series observations and user intent, autonomously decides when to remain silent or respond, and continues processing new observations during response generation. To realize this, we develop TimeInteract with three key designs: a dual-view streaming TS encoder that captures local variations and historical dynamics, a response control mechanism that learns when to trigger a response, and a decoupled streaming inference mechanism that separates control from response generation to avoid blocking subsequent observations. We further formulate a hierarchy of interaction capabilities, progressing from Understanding to Adaptivity. Based on this hierarchy, we construct StreamTSI-34K, a large-scale streaming TS interaction dataset with 34,588 episodes and 77,505 responses across synthetic and real-world time series in single- and multi-turn settings. Across all four interaction levels, TimeInteract consistently outperforms existing LLMs, VLMs, and TSLMs, with gains of up to 23.92 points on challenging tasks. It also improves response triggering while achieving near-zero stream stall and up to $2.15\times$ inference speedup. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.26389 — 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 2026-10-08T13:18:38.313Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).