PulseAugur
中
实时 08:37:23
English(EN) Cowork-Gym: Synthesizing Interactive Work Environments at Scale

新框架合成 64K 交互式环境用于 AI 代理训练

研究人员开发了 Cowork-Gym,一个旨在为训练 AI 代理合成交互式工作环境的框架。该系统使用构建-执行-修订循环来创建和验证这些环境,并包含一个通过对话和工作区编辑进行交互的用户模拟器。该框架已在 14 个场景中生成了超过 64,000 个环境,并用于微调不同大小(9B、27B 和 35B-A3B)的 Qwen 模型。这些微调后的模型在代理基准测试中表现出显著的改进,其中 27B 模型在 PAWBench 和 ClawEval 上取得了最佳性能,超越了更大的模型。 AI

影响 增强了 AI 代理在复杂、交互式环境中的能力,可能提高协作任务的性能。

排序理由 该集群包含一篇详细介绍新框架及其在训练 AI 模型中的应用的学术论文。[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 →

新框架合成 64K 交互式环境用于 AI 代理训练

本文如何被排名

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍新框架及其在训练 AI 模型中的应用的学术论文。[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, model release
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) · Anni Zou, Cheng Chen, Jiaji Deng, Weikang Zhou, Xinji Mai, Yue Wu, Jianing Lin, Lipeng Xie, Lixiong Qin, Qingyue Zhao, Que Shen, Shuchang Tao, Xuchen Pan, Yaliang Li, Yunpeng Zhai, Yushuo Chen, Zhihai Wang, Zhuo Zhang, Zhaoyang Liu, Bolin Ding, Jingren Z… ·

    Cowork-Gym:大规模合成交互式工作环境

    arXiv:2610.17670v1 Announce Type: new Abstract: Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable res…