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.

The MEDIQA-EVAL 2026 shared task focuses on developing automatic evaluation metrics for LLM-generated responses in dermatology and wound care. While LLMs have shown promise as judge models, the reliability of these metrics remains underexplored. In this work, we study how well judge models can approximate human expert ratings across clinical evaluation criteria. We evaluate multiple approaches, including few-shot prompting, BERT fine-tuning, and retrieval-augmented generation (RAG), and combine them in an ensemble framework. Our method achieves a correlation score of 0.481, ranking first among 41 participating teams. Our results provide insight into the reliability of LLM-based evaluation metrics and highlight their potential for scalable clinical assessment.