# KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning

arXiv: https://arxiv.org/abs/2605.30002 · HTML: https://mlsanity.com/paper/2605.30002/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)
- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [Moirai 2.0: When Less Is More for Time Series Forecasting](https://mlsanity.com/paper/2511.11698/) (2025)
- [GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning](https://mlsanity.com/paper/2402.16829/) (2024)
- [TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis](https://mlsanity.com/paper/2410.04047/) (2024)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models](https://mlsanity.com/paper/2509.24803/) (2025)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain](https://mlsanity.com/paper/2310.05063/) (2023)
- [LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction](https://mlsanity.com/paper/2304.14343/) (2023)
- [SciTS: Scientific Time Series Understanding and Generation with LLMs](https://mlsanity.com/paper/2510.03255/) (2025)
- [Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting](https://mlsanity.com/paper/2602.13802/) (2026)
- [Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models](https://mlsanity.com/paper/2509.25826/) (2025)
- [Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting](https://mlsanity.com/paper/2512.16022/) (2025)
- [Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkit](https://mlsanity.com/paper/2307.07191/) (2023)
- [FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series](https://mlsanity.com/paper/2508.19279/) (2025)
- [TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts](https://mlsanity.com/paper/2602.21693/) (2026)
- [Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models](https://mlsanity.com/paper/2510.07858/) (2025)

## Built on by (most cited first, 5 of 5)

- [LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications](https://mlsanity.com/paper/2608.23058/) (2026)
- [When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting](https://mlsanity.com/paper/2609.24862/) (2026)
- [Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning](https://mlsanity.com/paper/2609.32689/) (2026)
- [ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.35532/) (2026)
- [Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning](https://mlsanity.com/paper/2610.04942/) (2026)

## Abstract (arXiv)

Cross-domain multimodal time series forecasting is a challenging task, requiring models to integrate precise numerical comprehension, cross-domain semantic understanding, and effective multimodal fusion. Existing approaches either build Time Series Foundation Models (TSFMs) from scratch or leverage pretrained Large Language Models (LLMs). However, TSFMs often overlook semantic understanding and lack the ability to perform future-oriented semantic reasoning, and LLMs struggle with numerical comprehension and accurate quantitative forecasting. To overcome these limitations, we propose KairosAgent, a novel agentic framework for multimodal time series forecasting, including an LLM-based reasoner and a TSFM-based forecaster. KairosAgent unifies textual reasoning and numerical forecasting by dynamically invoking analytical tools to enhance the numerical understanding and semantic reasoning capabilities of LLMs. The reasoning results are subsequently fused into the TSFM pipeline, enabling more accurate and reliable future predictions. To further improve the reasoning, we curate a large-scale corpus of high-quality trajectories, alongside a reinforcement learning from forecasting paradigm with multi-turn refinement and turn-level credit assignment. Experiments demonstrate that KairosAgent achieves superior zero-shot forecasting performance while maximizing the utility of pretrained LLMs and TSFMs, presenting a promising direction for efficient and interpretable time series agents. The project page is at https://foundation-model-research.github.io/KairosAgent .