English(EN) WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

WorkFactory框架将Qwen模型训练成WorkPilot代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了WorkFactory，一个旨在为训练AI代理创建多样化且可执行的专业任务的框架。该系统使用信息级规划来构建信息支持图，指导任务实例化并识别潜在故障。该框架已用于生成跨越600种职业的112,000多个任务，随后用于微调Qwen模型，从而产生了WorkPilot系列代理。这些WorkPilot模型在专业工作基准测试中表现出显著的改进，其中WorkPilot-35B-A3B在GDPval-AA v2.1上的Elo分数有了显著提高。 AI

影响引入了一种可扩展的方法来生成多样化的训练数据，以提高AI代理在专业任务上的性能。

排序理由学术论文，详细介绍了一个新框架和模型训练方法。 [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 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一个新框架和模型训练方法。 [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]

arXiv cs.AI TIER_1 English(EN) · Ziyang Zeng, Tingyang Chen, Jia Deng, Qiyao Wang, Shuo Tang, Yike Yang, Tao Ren, Wayne Xin Zhao, Feng Chang, Jujie He, Chuan Hao, Ran Tao, Bryan Dai · 2026-10-28 04:00

WorkFactory：将专业意图转化为可执行工作，以实现可扩展的代理训练

arXiv:2610.37161v1 Announce Type: new Abstract: Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can obstruct teacher execution and weaken the resulting …

本文如何被排名

报道来源 [1]

WorkFactory：将专业意图转化为可执行工作，以实现可扩展的代理训练

相关实体

相关话题