腾讯混元推出 WorkForge 框架，从真实工作流构建 16.7K 个可验证智能体训练环境

摘要

腾讯混元推出 WorkForge 框架，从真实世界资源为长程工作智能体构建可验证的训练环境，做法是从专家工作流出发搭建真实工作空间、抽取可核查事实，并据此生成任务和程序化与语义双重验证器。

摘要由模型根据原文撰写，以原文为准。

📢 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

TencentHunyuan. 📢 Introducing WorkForge: a scalable framework that constructs verifiable training environments for long-horizon work agents from real-wo...[EB/OL]. (2026-10-22)[访问日期]. https://x.com/TencentHunyuan/status/2113196619667763211.

腾讯混元推出 WorkForge 框架，从真实工作流构建 16.7K 个可验证智能体训练环境

摘要

正文 · 原文

引用原文