PulseAugur
中
实时 08:29:26
English(EN) daVinci-Env: Open SWE Environment Synthesis at Scale

OpenSWE框架为代理训练合成45k个软件工程师环境

研究人员开发了OpenSWE,一个用于训练软件工程(SWE)代理的大规模、透明的框架。该框架包含超过45,000个可执行的Docker环境,这些环境源自12,000多个代码库,所有相关代码和基础设施均公开可用以保证可复现性。该项目涉及一个多代理合成管道和一个质量过滤过程,以确保环境的有效性,总成本约为147万美元。实验表明,使用OpenSWE训练的模型,如OpenSWE-32B和OpenSWE-72B,在SWE-bench Verified基准测试中取得了最先进的成果,并在其他推理和科学任务中显示出显著的改进。 AI

影响 为在软件工程任务中训练和评估AI代理提供了一个可扩展的开源环境,有可能加速该领域的进展。

排序理由 该集群描述了一篇关于用于训练AI代理的新颖框架和数据集的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

OpenSWE框架为代理训练合成45k个软件工程师环境

本文如何被排名

Signal score
19 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇关于用于训练AI代理的新颖框架和数据集的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng, Mohan Jiang, Lin Zhang, Yukun Li, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu ·

    daVinci-Env: 大规模开放软件工程师环境合成

    arXiv:2603.13023v3 Announce Type: replace-cross Abstract: Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. Howev…