EnvHarness：唤醒静态世界以促进智能体学习

AI 摘要

EnvHarness 提出了一种可编程插件层，通过动态重塑静态环境来针对智能体的弱点进行强化学习共进化。EnvRigger 将目标策略视为黑盒，通过观察执行轨迹合成组件并验证。在四个领域的五个基准测试中，EnvHarness 优于原始环境和领域特定的环境生成流程，在保留实例上实现了最高 9.0 分的提升，并减少了 9.8% 的执行步骤。

正文节选

EnvHarness: Awakening Static Worlds for Agent Learning Abstract EnvHarness and EnvRigger dynamically reshape static environments via programmable plugins to target agent weaknesses and improve reinforcement learning co-evolution. 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

发布时间：—

抓取时间：2026-08-21 10:45

来源机构：Hugging Face