发表机构
Columbia University; Georgetown University; Capital One（哥伦比亚大学; 乔治城大学; 第一资本金融公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对自动研究智能体应用于表格数据集时的四类计算资源浪费问题，提出针对性干预措施，仅通过优化智能体设计即可大幅提升其性能。
AI 中文摘要
近期大量研究开发了用于端到端解决研究问题的智能体，该范式逐渐被称为自动研究（autoresearch）。这类智能体因具备自动化耗时人力劳动、为特定应用定制机器学习解决方案的潜力，已吸引了大量行业投资。本文研究自动研究系统核心的建模流程，识别其应用于表格数据集时的常见失效模式：（1）浪费计算资源反复解决相同的错误；（2）即便剩余计算预算充足，也常无法调整超参数；（3）支撑系统的树搜索算法缺乏探索性；（4）执行数据分析时模仿其训练所用的人类，但不会利用该分析做出下游决策。我们探索针对性干预措施，发现能在搜索树所有分支间共享已发现运行时约束的全局调试顾问、提示与控制层面的增强，以及改进后的树搜索算法，可成功恢复浪费的计算资源。结果显示，仅通过智能体设计，在保持底层语言模型固定的情况下，即可实现自动研究智能体性能的大幅提升。
英文摘要
A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have inspired large industry investment, motivated by their potential to automate time-consuming human labor and customize machine learning solutions for specialized applications. In this paper, we study the modeling pipeline at the core of these autoresearch systems and identify common failure modes when they are applied to tabular datasets: (1) they waste compute resolving the same bugs over and over again; (2) they often fail to tune hyperparameters even when they have a large remaining compute budget; (3) the tree-search algorithms that power them do not explore; and (4) they perform data analysis, mimicking the humans whose data they are trained on, but do not use that analysis to make downstream decisions. We explore targeted interventions and find that a global debug consultant that shares discovered runtime constraints across all branches of the search tree, prompt- and control-level enhancements, and refined tree-search algorithms successfully recover wasted compute. Our results show that large gains in autoresearch agent performance are achievable through agentic design alone, holding the underlying language model fixed.
