发表机构
The Chinese University of Hong Kong, Shenzhen; City University of Hong Kong; Sun Yat-Sen University（香港中文大学（深圳）; 香港城市大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出首个面向无线领域的端到端闭环LLM自动研究框架WARA，通过工件介导控制实现自动化无线优化研究，其性能优于单次LLM生成，接近同行评审论文质量。
AI 中文摘要
大型语言模型（LLM）智能体在工具使用、代码执行、工件检查和迭代修订方面的能力日益增强，为自动化科学与工程研究创造了新机遇。据我们所知，本文提出了首个面向无线领域的端到端自动研究框架，聚焦无线资源分配优化。我们提出了Wireless AutoResearch Agent（WARA，无线自动研究智能体），这是一种用于自动化无线优化研究的闭环多智能体系统。仅给定初始主题，WARA将工作流分解为三个阶段：研究缺口识别与问题提出、无线优化建模、算法设计与实验，以及研究成果构建。在这些阶段中，WARA采用工件介导控制：上游工件作为输入被使用，结构化输出被存储以供下游使用，由控制器管理的门控机制验证模型、算法、实验和主张之间的一致性。当验证失败时，WARA仅修复负责的工件，而非重启整个工作流。我们展示了一个具有代表性的无线资源分配案例研究，表明WARA如何将初始主题转换为包含可执行证据和合成技术手稿的完整研究包。我们还设计了一种基于LLM的结构化ScoringAgent（评分智能体），用于评估手稿级别的研究有效性和优化研究成熟度。对比结果显示，WARA的性能显著优于单次LLM生成，且接近近期被同行评审接收的技术论文的质量水平。这些结果表明，闭环工件控制是实现端到端LLM辅助无线优化研究的有前景路径。源代码可在该https URL获取。
英文摘要
Large language model (LLM) agents are increasingly capable of tool use, code execution, artifact inspection, and iterative revision, creating new opportunities for automating scientific and engineering research. To the best of our knowledge, this paper presents the first end-to-end autoresearch framework for the wireless domain, with a focus on wireless resource allocation optimization. We propose the Wireless AutoResearch Agent (WARA), a closed-loop multi-agent system for automated wireless optimization research. Given only an initial topic, WARA decomposes the workflow into three phases: research gap identification and problem proposal, wireless optimization modeling, algorithm design and experimentation, and research deliverable construction. Across these phases, WARA uses artifact-mediated control: upstream artifacts are consumed as inputs, structured outputs are stored for downstream use, and controller-managed gates validate consistency among models, algorithms, experiments, and claims. When validation fails, WARA repairs only the responsible artifact instead of restarting the whole workflow. We present a representative wireless resource allocation case study showing how WARA converts an initial topic into a complete research package with executable evidence and a synthesized technical manuscript. We further design a structured LLM-based ScoringAgent to evaluate manuscript-level research validity and optimization research maturity. Comparative results show that WARA substantially outperforms one-shot LLM generation and approaches the quality profile of recently accepted peer-reviewed technical papers. These results indicate that closed-loop artifact control is a promising path toward end-to-end LLM-assisted wireless optimization research. The source code is available at https://github.com/guoyuan-dotcom/WARA_CUHKSZ.
