Research map / Large language models / Agents, code and math
Zephyrus: An Agentic Framework for Weather Science
Sumanth Varambally, Marshall Fisher, Jas Thakker, Yiwei Chen, Zhirui Xia, Yasaman Jafari, Ruijia Niu, Manas Jain, Veeramakali Vignesh Manivannan, Zachary Novack, Luyu Han, Srikar Eranky and 5 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the Zephyrus agent with weather data tools instead of a text-only baseline | GPT-5-Mini · ZephyrusBench correctness | correctness (%): 17 -> 58.5 (Direct), 17 -> 61.2 (Reflective) | Improved |
| use Zephyrus agents instead of text-only across all LLMs | Zephyrus · ZephyrusBench correctness | correctness (%): 27.8-44.2% higher correctness | Improved |
| add multi-turn execute-observe reflection (Reflective vs Direct) with OpenAI models | Zephyrus · ZephyrusBench correctness | correctness (%): 0.8-2.7% higher | Improved |
| add multi-turn reflection (Reflective vs Direct) with Qwen3-30B and Gemini 2.5 Flash | Zephyrus · ZephyrusBench correctness | correctness (%) | Hurt |
| use Reflective instead of Direct on numerical tasks | Zephyrus with Qwen3-30B vs GPT-5.2 · ZephyrusBench numerical tasks | standardized absolute error | Mixed |
| use Reflective instead of Direct or text-only for descriptive report tasks | Zephyrus with GPT-5.2 · ZephyrusBench report generation | discussion score: best discussion score 0.27 | Improved |
Closest papers by meaning
- AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science (NeurIPS 2025 · similarity 0.87)
- WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning (ICLR 2025 · similarity 0.87)
- Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models (NeurIPS 2024 · similarity 0.87)
- Assessing Large Language Models on Climate Information (ICML 2024 · similarity 0.86)
- HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosis (ICML 2026 · similarity 0.86)
- WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation (ICML 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
