AI 训练环境的新玩法：先解出答案，再生成任务
训练 AI 智能体的最大瓶颈之一，是造不出足够多、足够难、又带明确答案的“虚拟考场”。现有做法通常是先搭场景、再补规则，结果常常是场景和评分标准对不上。这篇论文把顺序彻底反过来：先用数学方法把机制解出来，再让语言模型把解题过程渲染成可交互的工具环境。因为答案和评分标准来自同一个已解模型，环境天然自洽。用这套流程，他们以每个几美分的成本生成了 3300 个多样环境，把 Qwen3.6-35B 的平均智能体得分从 0.204 拉到 0.815，而且提升能迁移到没见过的机制族和外部基准（通用函数调用、旅行规划、365 天电商）。最值得注意的发现是：把问题写成文字版和做成可交互状态版对比，大部分学习差距来自“状态交互”本身，而不是底层解题能力——也就是说，让 AI 学会“在动态环境里做决定”比“解一道题”难得多，也重要得多。这不是你明天能直接用的工具，但它指向一个趋势：AI 训练环境正在从“人工搭场景”走向“自动生成且自带答案”，这可能是下一代智能体能力跃迁的燃料。
📄 原文摘要(英文)
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable outcome signals, and low extension cost. Existing generation pipelines commonly construct an environment before defining its outcome rule or annotating its trajectories, leaving dynamics and evaluation to be aligned post hoc. VHD-Play reverses this dependency by sampling and solving a mathematical model before a corpus-grounded setter renders its decision process as stateful tools. The executable dynamics and trajectory-scoring reference are inherited from the same solved model. The pipeline produces 3,300 diverse agentic environments at a cost of a few cents each. Training Qwen3.6-35B-A3B on three families raises its mean agentic score from 0.204 to 0.815 in a five-family diagnostic. Gains also appear on held-out instances from all three training families and eight unseen mechanism families, then extend beyond the generated substrate to external benchmarks for general function calling, travel planning, and 365-day e-commerce. On E-Commerce Bench, the trained checkpoint completes every run without bankruptcy and exceeds Qwen3.7-Max. We compare written-out problems with stateful versions that reveal or hide their parameters. The comparison shows that most of the learnable gap lies in stateful interaction rather than underlying problem solving. A frozen 35B setter realizes larger environments, and scale-matched training retains gains as mechanism size and horizon grow, indicating the potential for an evolving training substrate.