TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis

[2410.04047] TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2410.04047 (cs) [Submitted on 5 Oct 2024 ( v1 ), last revised 10 Apr 2026 (this version, v6)] Title: TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis Authors: Wen Ye , Wei Yang , Defu Cao , Yizhou Zhang , Lumingyuan Tang , Jie Cai , Yan Liu View a PDF of the paper titled TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis, by Wen Ye and 6 other authors View PDF HTML (experimental) Abstract: Time series analysis is crucial in real-world applications, yet traditional methods focus on isolated tasks only, and recent studies on time series reasoning remain limited to either single-step inference or are constrained to natural language answers. In this work, we introduce TS-Reasoner, a domain-specialized agent designed for multi-step time series inference. By integrating large language model (LLM) reasoning with domain-specific computational tools and an error feedback loop, TS-Reasoner enables domain-informed, constraint-aware analytical workflows that combine symbolic reasoning with precise numerical analysis. We assess the system's capabilities along two axes: (1) fundamental time series understanding assessed by TimeSeriesExam and (2) complex, multi-step inference evaluated by a newly proposed dataset designed to test both compositional reasoning and computational precision in time series analysis. Experiments show that our approach outperforms standalone general-purpose LLMs in both basic time series concept understanding as well as the multi-step time series inference task, highlighting the promise of domain-specialized agents for automating real-world time series reasoning and analysis. Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2410.04047 [cs.LG] (or arXiv:2410.04047v6 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2410.04047 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Wen Ye [ view email ] [v1] Sat, 5 Oct 2024 06:04:19 UTC (776 KB) [v2] Tue, 8 Oct 2024 16:28:23 UTC (758 KB) [v3] Wed, 12 Feb 2025 00:23:36 UTC (1,347 KB) [v4] Thu, 22 May 2025 01:01:55 UTC (442 KB) [v5] Tue, 17 Mar 2026 07:30:20 UTC (615 KB) [v6] Fri, 10 Apr 2026 06:16:18 UTC (615 KB) Full-text links: Access Paper: View a PDF of the paper titled TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis, by Wen Ye and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2024-10 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• TTSR: Test-Time Self-Evolving via Reflection#1014626
• Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation#986796
• Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models#324897
• HeteroReason: Heterogeneous FPGA-GPU Acceleration for Disaggregated Speculative Reasoning#1076373
• MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference#1155072