模型精选

腾讯混元发布 WorkForge:用真实工作流构建可验证的 Agent 训练环境

精选理由

腾讯混元开源了 WorkForge,能把专家工作流自动变成 16.7K 个可验证的 Agent 训练环境,做长程工作 Agent 训练的可以看看这篇论文。

腾讯混元推出 WorkForge 框架,从专家工作流出发构建真实的办公工作区,并提取可核查的事实来生成任务。每个任务配有程序化和语义化双重验证器,均基于可观察证据。该框架扩展到 16.7K 个环境,覆盖 40 个专业领域和 60 种文件类型。随着数据量和交互时长增加,长程工作类基准上的成绩持续提升。

原文 · 腾讯混元

Introducing WorkForge: a scalable framework that constructs verifiable training environments for long-horizon work agents from real-world resources.

Starting from expert workflows, it builds authentic workspaces, extracts checkable facts, and derives tasks plus dual (programmatic + semantic) verifiers grounded in observable evidence.

We scale to 16.7K environments across 40 professional domains covering 60 file types, enabling consistent gains on long-horizon work benchmarks as data volume and interaction horizon increase.

Paper: https://t.co/HjswwiHhlv @zhang_leo54389

#Tencent Hy#AIAgents #WorkAgents #AgentTraining