腾讯混元发布 WorkForge 框架,可从真实世界资源构建可验证的长周期工作智能体训练环境,覆盖 40 个专业领域、60 种文件类型,共 16.7K 个环境。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,并生成任务及程序化与语义双重验证器。随数据量和交互时长增加,长周期工作基准上的收益持续提升。
📢 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://arxiv.org/pdf/2610.04906 @zhang_leo54389 @ZoeyyyZhououou @Be1ong1
#Tencent Hy#AIAgents #WorkAgents #AgentTraining
来源:Tencent Hy · x.com