ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis

• URL: http://arxiv.org/abs/2604.16922v2
• Date: Sat, 25 Apr 2026 10:55:06 GMT
• Title: ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis
• Abstract summary: We introduce ClimAgent, a framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields.<n>By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis.<n>ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality.
• Score: 15.602458015516042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.

Related papers

• Unfolding the Interdisciplinary Complexities of Climate Science: Fuxi-Climate Foundational Model [17.32455386909819]
  Fuxi-Climate Foundation Model (CFM) designed to support consistent reasoning across domains.<n>On expert-designed climate transition tasks, CFM produces more structured analyses that explicitly address trade-offs and uncertainty.<n>These results indicate that CFM can support more realistic analysis of climate risks and transition pathways.
  arXiv  Detail & Related papers  (2026-08-23T06:43:42Z)
• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration [63.61423859450929]
  This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses.<n>We identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery.
  arXiv  Detail & Related papers  (2026-01-20T18:46:42Z)
• What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding [50.35012849818872]
  Large language model (LLM) agents have demonstrated remarkable capabilities in complex decision-making and tool-use tasks.<n>We propose Task-to-Quiz (T2Q), a deterministic and automated evaluation paradigm designed to decouple task execution from world-state understanding.<n>Our experiments reveal that task success is often a poor proxy for environment understanding, and that current memory machanism can not effectively help agents acquire a grounded model of the environment.
  arXiv  Detail & Related papers  (2026-01-14T14:09:11Z)
• EWE: An Agentic Framework for Extreme Weather Analysis [61.092871317626496]
  Extreme Weather Expert (EWE) is first intelligent agent framework dedicated to this task.<n>EWE emulates expert visualizations through knowledge-guided planning, closed-loop reasoning, and a domain-tailored meteorological toolkit.<n>To catalyze progress, we introduce the first benchmark for this emerging field, comprising a curated dataset of 103 high-impact events.
  arXiv  Detail & Related papers  (2025-11-26T14:37:25Z)
• CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows [9.678989760151575]
  We present ClimateAgent, an autonomous multi-agent framework that orchestrates end-to-end climate data analytic tasks.<n>On Climate-Agent-Bench-85, ClimateAgent achieves 100% task completion and a report quality score of 8.32, outperforming GitHub-Copilot (6.27) and a GPT-5 baseline (3.26)<n>Results demonstrate that our multi-agent orchestration with dynamic API awareness and self-correcting execution substantially advances reliable, end-to-end automation for climate science analytic tasks.
  arXiv  Detail & Related papers  (2025-11-25T09:27:33Z)
• Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM [4.330506300153804]
  We present a multi-agent reinforcement learning framework that integrates a high-fidelity, highly efficient climate surrogate directly in the environment loop.<n>As a proof of concept, we introduce a recurrent neural network architecture pretrained on ($20,000$) multi-gas emission pathways to surrogate the climate model CICERO-SCM.<n>The surrogate model attains near-simulator accuracy with global-mean temperature RMSE $approx 0.0004 mathrmK$ and approximately $1000times$ faster one-step inference.
  arXiv  Detail & Related papers  (2025-10-09T09:02:49Z)
• ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows [82.07367406991678]
  Large Language Models (LLMs) have extended their impact beyond Natural Language Processing.<n>Among these, computer-using agents are capable of interacting with operating systems as humans do.<n>We introduce ScienceBoard, which encompasses a realistic, multi-domain environment featuring dynamic and visually rich scientific software.
  arXiv  Detail & Related papers  (2025-05-26T12:27:27Z)
• AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science [9.757412158154514]
  We present a novel benchmark designed to assess large language models (LLMs) across five core categories of atmospheric science problems.<n>AtmosSci-Bench features a dual-format design comprising both multiple-choice questions (MCQs) and open-ended questions (OEQs)<n>We conduct a comprehensive evaluation of representative LLMs, categorized into four groups: instruction-tuned models, advanced reasoning models, math-augmented models, and domain-specific climate models.
  arXiv  Detail & Related papers  (2025-02-03T08:50:46Z)
• On the Opportunities of (Re)-Exploring Atmospheric Science by Foundation Models: A Case Study [2.672038860046272]
  Most state-of-the-art AI applications in atmospheric science are based on classic deep learning approaches. This report explores how the state-of-the-art foundation model, i.e., GPT-4o, performs various atmospheric scientific tasks.
  arXiv  Detail & Related papers  (2024-07-25T07:57:34Z)
• DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents [49.74065769505137]
  We introduce DISCOVERYWORLD, the first virtual environment for developing and benchmarking an agent's ability to perform complete cycles of novel scientific discovery. It includes 120 different challenge tasks spanning eight topics each with three levels of difficulty and several parametric variations. We find that strong baseline agents, that perform well in prior published environments, struggle on most DISCOVERYWORLD tasks.
  arXiv  Detail & Related papers  (2024-06-10T20:08:44Z)
• HECT: High-Dimensional Ensemble Consistency Testing for Climate Models [1.7587442088965226]
  Climate models play a crucial role in understanding the effect of environmental changes on climate to help mitigate climate risks and inform decisions. Large global climate models such as the Community Earth System Model (CESM), are very complex with millions of lines of code describing interactions of the atmosphere, land, oceans, and ice. Our work uses probabilistics like tree-based algorithms and deep neural networks to perform a statistically rigorous goodness-of-fit test of high-dimensional and man-made data.
  arXiv  Detail & Related papers  (2020-10-08T15:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.