发表机构
School of Automation and Intelligent Science, Jiangnan University; School of Automation, Southeast University（江南大学自动化与智能科学学院; 东南大学自动化学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EvoCast是一种全自主研究智能体系统，通过认知-权威分离设计，实现迭代式预测架构演化，以更高实现成功率、更低成本开发出优于基线的任务特定架构。
AI 中文摘要
深度时间序列预测模型已迅速多样化，但将其适配到特定任务仍需要专家在模型选择、机制诊断、架构设计、实现和评估方面付出大量努力。现有的AutoML方法受限于预定义的搜索空间，而通用LLM研究智能体缺乏对实验协议和模型提升的可靠控制。我们引入了EvoCast，一个用于迭代式预测架构演化的全自主研究智能体系统。EvoCast首先通过执行的机制消融建立并诊断任务特定的基线，然后从数据集特征、诊断结果、先前轮次和失败记录中生成基于证据的研究方向。其核心设计，认知-权威分离，将开放式假设生成和代码实现分配给LLM智能体，而确定性程序权威控制源代码编辑边界、规范评估和提升决策。实验结果作为证据累积以指导后续轮次。结果表明，EvoCast以更高的实现成功率和更低的智能体端token/时间成本完成复杂的架构修改，并在三个真实世界预测案例中开发出优于所选基线、强预测模型和智能体基线的任务特定架构。代码可在https://this https URL获取。
英文摘要
Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model selection, mechanism diagnosis, architecture design, implementation, and evaluation. Existing AutoML methods are constrained by predefined search spaces, while general-purpose LLM research agents lack reliable control over experimental protocols and model promotion. We introduce EvoCast, a fully autonomous research-agent system for iterative forecasting architecture evolution. EvoCast first establishes and diagnoses a task-specific baseline through executed mechanism ablations, then generates evidence-grounded research directions from dataset characteristics, diagnostic results, prior rounds, and failure records. Its central design, cognition-authority separation, assigns open-ended hypothesis generation and code implementation to LLM agents, while deterministic program authorities control source-edit boundaries, canonical evaluation, and promotion decisions. Experimental outcomes are accumulated as evidence to guide subsequent rounds. Results show that EvoCast completes complex architecture modifications with higher implementation success and lower agent-side token/time cost, and develops task-specific architectures that outperform selected baselines, strong forecasting models, and agent baselines in three real-world forecasting cases. The code is available at https://github.com/18e0-x/EvoCast.
Comments26 pages, 11 figures, including references and appendices. Code: https://github.com/18e0-x/EvoCast
