LLMエージェントにおける世界モデルと方策の合成:スペクトル解析と行動解析による統一的考察
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
LLMエージェントの世界モデル学習と方策学習の相互作用を、パラメータ更新の幾何学的構造と行動特性の両面から分析し、逐次学習が頑健性と探索性を向上させることを示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ruize Xu, Xiao Yu, Yujin Tang, Chenming Shang, Nikhil Singh
分類: cs.LG, cs.AI, cs.CL
原文アブストラクト
How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state prediction) and policy training (reward maximization), we investigate this question. We dissect the resulting models through their additive parameter updates. Geometrically, we find effective world-model updates are low-rank and share an input-feature subspace with policy updates while writing to nearly orthogonal output directions, whether trained separately or sequentially. However, we find that, in projection interventions, the sequential update induces more robustness than separate policy RL when removing the world model's leading input directions, suggesting that it has learned alternative input pathways. Behaviorally, we find the sequentially trained agent explores a wider range of states and actions. Based on this, we ask: does policy training preserve world knowledge as well as it could? We probe this with training-free merging built on the geometrically motivated input basis plus an online world-model loss during policy RL, and show both improve over the untreated baseline. Our findings suggest world knowledge and task-directed ability can be learned in geometrically complementary forms, and that future post-training pipelines should consider how best to engineer the interface between them.