AlphaSpace：透過語義標記化與符號推理實現機器人行動

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning

March 24, 2025

作者: Alan Dao, Dinh Bach Vu, Bui Quang Huy

cs.AI

摘要

本文介紹了AlphaSpace，這是一種新穎的方法論，旨在增強大型語言模型（LLMs）在三維笛卡爾空間導航中的空間推理能力。AlphaSpace採用基於語義的分詞策略，通過專門的語義標記來編碼高度信息，並主要整合符號化的合成推理數據。這種方法使LLMs能夠通過將物體定位在特定的[x, y, z]座標上來精確操縱物體。實驗結果表明，AlphaSpace在操縱子任務上顯著優於現有模型，總準確率達到66.67%，而GPT-4o和Claude 3.5 Sonnet的準確率分別為37.5%和29.17%。

English

This paper presents AlphaSpace, a novel methodology designed to enhance the spatial reasoning capabilities of large language models (LLMs) for 3D Cartesian space navigation. AlphaSpace employs a semantics-based tokenization strategy, encoding height information through specialized semantic tokens, and integrates primarily symbolic synthetic reasoning data. This approach enables LLMs to accurately manipulate objects by positioning them at specific [x, y, z] coordinates. Experimental results demonstrate that AlphaSpace significantly outperforms existing models on manipulation subtasks, achieving a total accuracy of 66.67%, compared to 37.5% for GPT-4o and 29.17% for Claude 3.5 Sonnet.