Tencent Hunyuan releases WorkForge agent training framework
Training agents on verifiable, evidence-grounded tasks addresses the core bottleneck of RL for long-horizon work: reward reliability. The 16.7K-environment scale makes this one of the larger open efforts in agent environment construction. Engineers building work or office agents can study the dual-verifier design for their own training pipelines.
Tencent Hunyuan introduced WorkForge, a framework that builds verifiable training environments for long-horizon work agents from real-world expert workflows. It constructs authentic workspaces, extracts checkable facts, and generates tasks with dual programmatic and semantic verifiers grounded in observable evidence. The framework scales to 16.7K environments spanning 40 professional domains and 60 file types. Reported results show consistent gains on long-horizon work benchmarks as data volume and interaction horizon increase.
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
