腾讯混元推出 WorkForge，一个可从真实世界资源构建可验证训练环境的可扩展框架，面向长周期工作智能体。该框架从专家工作流出发搭建真实工作空间、抽取可核查事实，并派生任务及程序化与语义双重验证器，已扩展至覆盖 40 个专业领域、60 种文件类型的 16.7K 个环境。随着数据量和交互时长增加，其在长周期工作基准上带来持续稳定的提升。
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://arxiv.org/pdf/2610.04906 @zhang_leo54389
#Tencent Hy#AIAgents #WorkAgents #AgentTraining
来源：Tencent Hy · x.com