跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 24 天前AI 評分43

TSFLab:用於時間序列預測研究的自我改進、智能體無關工作台

TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research

AI 導讀

TSFLab 是一個自我改進、智能體無關的工作台,為編碼智能體提供共享資源,以支援時間序列預測研究及基準測試。在重現研究和基準測試中,TSFLab 的任務完成率提高 20-163%,每項已完成任務所需的新增 tokens 減少 11-66%。方法開發試點研究亦顯示,TSFLab 提高預測準確度,並減少 32.8-73.6% 新增 tokens 和 9.2-68.8% 開發時間。

正文

Published on Oct 29

Authors:

,

,

,

,

,

,

,

,

Abstract

TSFLab is a self-improving agent-agnostic workbench that equips coding agents with shared resources to reduce costs and automate maintenance for time series forecasting research and benchmarking.

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.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.40901

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.40901 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.40901 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.40901 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co