超越單純的環境規模擴展：為多模態智能體學習設計有效的環境分佈

摘要

近期的研究透過建構大規模多模態環境池來訓練智能體。然而，我們發現單純增加多模態環境的數量並不總是帶來益處。我們進一步透過一系列實驗分析當前多模態環境分佈的局限性。基於這些發現，我們從兩個維度研究如何建構更有效的訓練環境分佈：多樣性與難度結構。在多樣性方面，我們提出能力感知環境選擇（Ability-aware Environment Selection, AES）以取得多樣化的環境集合。在難度結構方面，我們提出階層式難度課程（Hierarchical Difficulty Curriculum, HDC），透過兩個難度層級組織課程學習：束縛弱化與狀態規模遞進。實驗結果顯示，AES 與 HDC 能有效提升多模態智能體的訓練成效。

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.