Metraipolis › archive › dc_08b37bca4887

TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series — arXiv:2608.03391

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03391
License (as archived)
CC0-1.0
Archived
2026-10-31T12:42:26.486Z
SHA-256 of the archived text
5aa7608df61352a37e0e16c725950db0c9a75691565857a805821e9e471abb66
Stable URL of this page
https://metraipolis.com/documento/dc_08b37bca4887

How to cite

TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series — arXiv:2608.03391 — arXiv (en), https://arxiv.org/abs/2608.03391 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08b37bca4887 (Metraipolis archive dc_08b37bca4887, sha256 5aa7608df61352a37e0e16c725950db0c9a75691565857a805821e9e471abb66)
BibTeX
@misc{dc08b37bca4887,
  title = {TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series — arXiv:2608.03391},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03391},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08b37bca4887; sha256 5aa7608df61352a37e0e16c725950db0c9a75691565857a805821e9e471abb66},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03391. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, financial services, and logistics, where brief evidence may hide inside long spans of high-frequency data. Time-Series Language Models (TSLMs) are able to ingest time series data and verbalize findings on anomalies in natural language; however, recent benchmarks report a decrease in retrieval performance at long contexts, mirroring failure modes in text, vision, and audio. In the text domain, Recursive Language Models (RLMs) can recover much of this lost performance by keeping context external to the large language model (LLM), allowing the model to query it through code. We present TimeRLM, an RLM formulation for time-series that sequentially manipulates the signal using code and vision capabilities. We further introduce AnomalyXL, a synthetic long-context anomaly localization benchmark with programmatically injected anomalies that require precise retrieval. We implement five different task categories and two variants: AnomalyXL-MCQ and AnomalyXL-Localize. TimeRLM outperforms every evaluated TSLM and single-pass baseline on four of the five AnomalyXL-Localize tasks, reaching 0.682 IoU on localization and 0.745 on classify-with-evidence, versus at most 0.329 and 0.072 across all baselines. We post-train TimeRLM using reinforcement learning. The resulting model further improves performance and requires approximately one-third as many agent interaction turns as its untrained base model to produce a final answer. On unseen real-world ECG, sleep and software observability recordings, the post-trained TimeRLM retains or improves performance, surpassing TSLMs despite being trained exclusively on synthetic data. Our findings suggest recursive interaction with time-series is an effective approach for long-horizon retrieval.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.03391 — 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 2026-10-31T12:31:30.353Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).