AI 智能体终于不用在死环境里练手了
AI 智能体（Agent）学习时，环境是静态的——它不会根据智能体的弱点自动调整，智能体一旦变强，环境就失效了。过去要改环境得重写代码或依赖昂贵验证器。这篇论文做了两件事：EnvHarness 是一个可插拔的组件层，像给游戏加 Mod 一样，不改底层逻辑就能重塑环境行为；EnvRigger 则像教练，观察智能体执行轨迹，自动诊断弱点并生成针对性组件。在四个领域的五个基准测试中，它比原始环境和专用生成方法都好，最高提升 9 个点，还少用 9.8% 的执行步数。这不是你明天能用的工具，但它指向一个趋势：AI 训练环境将从静态沙盒变成自适应训练场，智能体不再被固定考题限制。
📄 原文摘要(英文)
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive or unreliable verifiers, and still produce static environments. To alleviate the engineering burden of rebuilding environments from scratch, we propose Environment Harness (EnvHarness), a programmable layer of plug-in components that wraps a static environment to reshape its behavior without modifying the underlying logic. Operating through standard interfaces, EnvHarness applies across diverse domains while ensuring every reshaped environment retains its original verifier. To automate this process, we introduce EnvRigger, which treats the target policy as a black box, observing its execution trajectories to synthesize EnvHarness components targeting diagnosed flaws, and validating them via fresh rollouts. Across five benchmarks in four domains, EnvHarness outperforms both original environments and domain-specific environment generation pipelines, achieving up to a 9.0-point improvement on held-out instances with 9.8% fewer execution steps. Furthermore, EnvHarness provides a superior optimization signal for reinforcement learning, enabling continuous, targeted co-evolution of the policy and its environment.