{"ID":2859362,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.05950","arxiv_id":"2510.05950","title":"Training-Free Time Series Classification via In-Context Reasoning with LLM Agents","abstract":"Time series classification (TSC) spans diverse application scenarios, yet labeled data are often scarce, making task-specific training costly and inflexible. Recent reasoning-oriented large language models (LLMs) show promise in understanding temporal patterns, but purely zero-shot usage remains suboptimal. We propose FETA, a multi-agent framework for training-free TSC via exemplar-based in-context reasoning. FETA decomposes a multivariate series into channel-wise subproblems, retrieves a few structurally similar labeled examples for each channel, and leverages a reasoning LLM to compare the query against these exemplars, producing channel-level labels with self-assessed confidences; a confidence-weighted aggregator then fuses all channel decisions. This design eliminates the need for pretraining or fine-tuning, improves efficiency by pruning irrelevant channels and controlling input length, and enhances interpretability through exemplar grounding and confidence estimation. On nine challenging UEA datasets, FETA achieves strong accuracy under a fully training-free setting, surpassing multiple trained baselines. These results demonstrate that a multi-agent in-context reasoning framework can transform LLMs into competitive, plug-and-play TSC solvers without any parameter training. The code is available at https://github.com/SongyuanSui/FETATSC.","short_abstract":"Time series classification (TSC) spans diverse application scenarios, yet labeled data are often scarce, making task-specific training costly and inflexible. Recent reasoning-oriented large language models (LLMs) show promise in understanding temporal patterns, but purely zero-shot usage remains suboptimal. We propose...","url_abs":"https://arxiv.org/abs/2510.05950","url_pdf":"https://arxiv.org/pdf/2510.05950v2","authors":"[\"Songyuan Sui\",\"Zihang Xu\",\"Xia Hu\"]","published":"2025-10-07T14:07:43Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608632,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859362,"paper_url":"https://arxiv.org/abs/2510.05950","paper_title":"Training-Free Time Series Classification via In-Context Reasoning with LLM Agents","repo_url":"https://github.com/SongyuanSui/FETATSC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}