Search papers, labs, and topics across Lattice.
KairosAgent is introduced, an agentic framework for multimodal time series forecasting that combines an LLM-based reasoner with a TSFM-based forecaster. It addresses limitations of existing TSFMs (lack semantic understanding) and LLMs (struggle with numerical comprehension) by dynamically invoking analytical tools to enhance numerical understanding and semantic reasoning. The framework is trained using a large-scale corpus and a reinforcement learning from forecasting paradigm, achieving superior zero-shot forecasting performance.
LLMs can now forecast time series data with greater accuracy and interpretability by fusing their reasoning capabilities with traditional time series models in a novel agentic framework.
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 .
