超越环境规模扩展：设计有效的多模态智能体环境分布
原标题：Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
AI 摘要
该研究重新审视了多模态智能体训练中环境规模扩展的常见范式，发现单纯增加环境数量并不总能提升性能，多模态环境尤其容易产生负迁移和优化冲突。为此，作者提出能力感知环境选择（AES）和分层难度课程（HDC）两种方法，分别从多样性和难度结构两个维度设计更有效的环境分布。实验表明，精心设计的环境分布能显著优于朴素的环境扩展，并带来更好的训练效果和泛化能力。
正文节选
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning Abstract Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply increasing the number of multimodal environments does not always benefit. We further analyze the limitations in current multimodal environment distributions through a series of experiments. Based on these findings, we study how to build more effective training enviro