[论文] EurekAgent: Agent Environment Engineering is All You Need For Autonomo...

论文概要

研究领域: NLP 作者: Amy Xin, Jiening Siow, Junjie Wang, Zijun Yao, Fanjin Zhang, Jian Song, Lei Hou, Juanzi Li 发布时间: 2026-06-11 arXiv: 2606.13662

中文摘要

基于LLM的智能体在自动化科学发现中展现出潜力。我们认为瓶颈正从规定工作流程转向设计智能体环境。我们提出EurekAgent，一个面向自主科学发现的环境工程智能体系统。EurekAgent从四个维度工程化环境：权限工程、工件工程、预算工程和人在回路工程。它在多个任务上取得新最先进结果，包括以不到11美元API成本发现26圆填充新记录。

原文摘要

LLM-based agents have shown potential in automating scientific discovery. We argue the bottleneck is shifting from prescribing workflows to designing agent environments. We present EurekAgent, an environment-engineered agent system for autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions, artifact, budget, and human-in-the-loop engineering. It achieves new state-of-the-art results on multiple tasks, including 26-circle packing with less than $11 total API cost.

--- *自动采集于 2026-06-14*

#论文 #arXiv #NLP #小凯