腾讯推出 WorkForge：为长程工作 Agent 构建可验证训练环境
腾讯混元开源了一个给工作型 Agent 造训练环境的框架，40 个领域、1.67 万个环境，训练数据还能自动验证，做 Agent 的可以看看。
腾讯混元发布 WorkForge 框架，从专家工作流出发生成真实工作空间，并提取可核查事实来构建任务。每项任务配套程序化与语义双重验证器，依据可观察证据判定完成情况。该框架已扩展到 16.7K 个环境，覆盖 40 个专业领域和 60 种文件类型。实验显示，随着数据量和交互时长增加，Agent 在长程工作基准上的成绩持续提升。
📢 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://t.co/HjswwiHhlv @zhang_leo54389 @ZoeyyyZhououou @Be1ong1
#Tencent Hy#AIAgents #WorkAgents #AgentTraining
