优化多模态智能体训练环境分布，提升学习效果
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
- 按能力筛选环境以增强多样性
- 分层级设计难度课程，逐步提升挑战性
- 适合多模态智能体训练与强化学习研究者
近期工作通过构建大规模多模态环境池来训练智能体。然而我们发现，单纯增加多模态环境数量并不总能带来收益。通过一系列实验，我们分析了当前多模态环境分布的局限性。基于此，从多样性和难度结构两个维度出发，提出更有效的训练环境分布设计：针对多样性，提出能力感知环境选择（AES）以获取多样化环境集合；针对难度结构，提出分层难度课程（HDC），通过驯化削弱和状态规模递进实现课程学习。实验表明，AES与HDC能有效提升多模态智能体的训练效果。
原文摘要 · Abstract (English)
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 environment distributions from two dimensions: **diversity** and **difficulty structure**. For diversity, we propose **Ability-aware Environment Selection (AES)** to obtain diverse environment sets. For difficulty structure, we propose **Hierarchical Difficulty Curriculum (HDC)**, which organizes curriculum learning through two difficulty levels: harness weakening and state-scale progression. Experiments show that AES and HDC effectively improve multimodal agent training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。