arXiv cs.AI· ChengAo Shen, Yanjun Zhao, Haoxin Liu, Bonnie Chen, Miles Ma, Dongjin Song, Hanghang Tong, Qingsong Wen, Jingrui He, Jingchao Ni·· 1 天前AI 评分38
TSFLab：面向时间序列预测研究的自改进、智能体无关工作台
TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research
AI 导读
TSFLab 是一个自改进、与智能体无关的时间序列预测研究工作台，为兼容的编码智能体提供共享资源与工具，支持低成本复现、基准测试和新方法开发。在复现与基准测试中，TSFLab 将任务完成率提升 20-163%，每个完成任务的新鲜 token 消耗降低 11-66%。智能体驱动方法开发的初步研究显示预测精度提升，新鲜 token 减少 32.8-73.6%，开发时间缩短 9.2-68.8%。
正文 · 原文
Abstract: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.
| Comments: | Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.40901 [cs.LG] |
| (or arXiv:2610.40901v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40901 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: ChengAo Shen [view email]
[v1]
Thu, 29 Oct 2026 19:22:33 UTC (1,137 KB)
来源：arXiv cs.AI · arxiv.org