エージェント方策は毎ステップ見る必要があるのか？推論と行動のための幾何学的抽象化
Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action
ロボット操作において、生の視覚観測を毎ステップ再解釈する代わりに、3D幾何学的抽象化をテキスト・記号で言語モデルに読ませる手法を提案し、多段階操作の成功率を向上させつつマルチモーダル問い合わせを大幅削減した。
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: Yihang Liu, Yiming Chen, Mingzhe Zheng
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Recent multimodal language models can reason directly about robot scenes, but it is unclear whether they need to repeatedly reinterpret raw visual observations at every step of an interaction. We propose shifting routine spatial reasoning from images to text and symbols through a 3D geometric abstraction that is refreshed locally from observations and read directly by the language models. Specifically, our interface represents scene geometry via typed, evidence-aware symbolic references to object parts, grounds them from calibrated RGB-D, and returns compact textual checkpoints with metric residuals after each action. Symbolic task structure can thus be reused across decisions while metric values are rebound to the current scene, with direct visual reasoning invoked only on demand. Across offline policy synthesis and continuous online execution, reasoning over grounded text and symbols improves multi-step manipulation completion while substantially reducing repeated multimodal queries, positioning explicit geometric state as an effective substrate for agentic robot policies.