mlsanityData to 7 Oct 2026

OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning

arXiv 2609.40265 ↗First posted 30 Sep 2026cs.LGcited by 0

On the map: LLM reasoning → Time series reasoning

Abstract (arXiv)

Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-based temporal reasoning. Yet current time-series foundation models remain fragmented across these capabilities: numerical specialists often provide the strongest forecasts, while language-based models offer broader contextual understanding and analysis. A central challenge is to unify these heterogeneous capabilities without reducing their individual performance. We introduce OpenTSLM TeeMoE, a generalist time-series language model that can forecast directly from observed time series, reason over textual context and temporal patterns, and synthesize and refine predictions from external numerical forecasting specialists. We independently train three low-rank experts for forecast aggregation, native forecasting, and temporal analysis over a shared backbone. A learned LoRA mixture-of-experts controller then weights their frozen parameter updates for each request. Our proposed model achieves strong performance on widely used benchmarks for time series forecasting, context-conditioned prediction, and language-based temporal reasoning, ranking among the top three on GIFT-Eval by mean MASE rank, Context is Key by RCRPS, and TimeSeriesExam by accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Time series reasoning, one of 17 directions in LLM reasoning. Builds on 62 of its 72 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

62 of 72 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Can LLM Coding Agents Reason About Time Series?15 Jun
  2. 2026Reasoning-Aware Training for Time Series Forecasting9 May
  3. 2026LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics19 Apr
  4. 2026TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale11 Apr
  5. 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning8 Feb
  6. 2025TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering8 Oct
  7. 2025TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning3 Oct
  8. 2025OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data2 Oct
  9. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning4 Dec
  10. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis5 Oct

Other references · 52

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  6. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  7. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  8. 2024Chronos: Learning the Language of Time Seriescited by 712
  9. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  10. 2023A decoder-only foundation model for time-series forecastingcited by 650
  11. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  12. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
38 more
  1. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  2. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  3. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  4. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 188
  5. 2024Mixture of LoRA Expertscited by 179
  6. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  7. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  8. 2025Chronos-2: From Univariate to Universal Forecastingcited by 158
  9. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 107
  10. 2023Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingcited by 102
  11. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  12. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 92
  13. 2024Context is Key: A Benchmark for Forecasting with Essential Textual Informationcited by 78
  14. 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 74
  15. 2024Towards Modular LLMs by Building and Reusing a Library of LoRAscited by 72
  16. 2025Moirai 2.0: When Less Is More for Time Series Forecastingcited by 59
  17. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 57
  18. 2024TimeSeriesExam: A time series understanding examcited by 47
  19. 2024Toto: Time Series Optimized Transformer for Observabilitycited by 44
  20. 2024X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Designcited by 41
  21. 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Datasetcited by 35
  22. 2025TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Modelscited by 24
  23. 2026Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scalingcited by 24
  24. 2026Toto 2.0: Time Series Forecasting Enters the Scaling Eracited by 21
  25. 2026Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Modelscited by 10
  26. 2026TiRex-2: Generalizing TiRex to Multivariate Data and Streamingcited by 10
  27. 2025When Does Multimodality Lead to Better Time Series Forecasting?cited by 9
  28. 2025FlowState: Sampling-Rate-Equivariant Time-Series Forecastingcited by 7
  29. 2025Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Modelscited by 7
  30. 2026ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Responsecited by 5
  31. 2025TsLLM: Augmenting LLMs for General Time Series Understanding and Predictioncited by 4
  32. 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generationcited by 4
  33. 2025Test-Time Efficient Pretrained Model Portfolios for Time Series Forecastingcited by 2
  34. 2026Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecastingcited by 2
  35. 2026Harnessing Generalist Agents for Contextualized Time Seriescited by 2
  36. 2023On tracking varying bounds when forecasting bounded time seriescited by 1
  37. 2026Overcoming the Modality Gap in Context-Aided Forecastingcited by 1
  38. 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditionscited by 1

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
  2. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  3. 2025STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
  4. 2024Language Models Still Struggle to Zero-shot Reason about Time Series
  5. 2025Context information can be more important than reasoning for time series forecasting with a large language model
  6. 2026CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting
  7. 2024Implicit Reasoning in Deep Time Series Forecasting
  8. 2026TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting