Metraipolis › archive › dc_cd97f1e5eefc
TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research — arXiv:2610.40901
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40901
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:09:51.760Z
- SHA-256 of the archived text
18a69f9e3d66c10aad78617ed9dff00b10448102deb5ae676469fd423ba205d2- Stable URL of this page
https://metraipolis.com/documento/dc_cd97f1e5eefc
How to cite
TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research — arXiv:2610.40901 — arXiv (en), https://arxiv.org/abs/2610.40901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd97f1e5eefc (Metraipolis archive dc_cd97f1e5eefc, sha256 18a69f9e3d66c10aad78617ed9dff00b10448102deb5ae676469fd423ba205d2)
BibTeX
@misc{dccd97f1e5eefc,
title = {TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research — arXiv:2610.40901},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40901},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd97f1e5eefc; sha256 18a69f9e3d66c10aad78617ed9dff00b10448102deb5ae676469fd423ba205d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As publications and products on time series forecasting (TSF) proliferate, researchers face a growing burden of analyzing existing work. First, not all publications release code. For instance, only about 20% of arXiv TSF papers have a code link in the surveyed period. Second, released code also requires manual maintenance. Thus, TSF researchers must constantly adapt or implement existing works. However, independent implementations can differ in experimental settings and are difficult to maintain. We therefore propose to use AI agents for benchmarking TSF research and even supporting autoresearch, e.g., developing new TSF models. Yet directly applying existing coding agents, such as Claude Code and Codex, is suboptimal: prohibitive costs, limited scalability to large research projects (e.g., benchmarking), and lack of self-maintenance. To address these challenges, we propose TSFLab, a self-improving agent-agnostic "workbench" that equips compatible coding agents with shared resources and tools for low-cost TSF research and continuous maintenance of research resources. Our experiments cover reproduction, benchmarking, and new method development. In reproduction and benchmarking, TSFLab improves task completion by 20-163% and cuts fresh tokens per completed task by 11-66% across baselines. A pilot study of agent-driven method development also shows improved forecasting accuracy via TSFLab, with 32.8-73.6% fewer fresh tokens and 9.2-68.8% less development time than the other settings. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.40901 — 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 2026-11-02T07:06:59.404Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).