LATIDIA · Robótica

LogicEnvGen: Generación impulsada por la lógica de tareas de diversos entornos simulados para IA incorporada

arXiv: 2601.13556v2Tipo de anuncio: reemplazar Resumen: Los entornos simulados desempeñan un papel esencial en la IA incorporada, funcionalmente análogo a los casos de prueba en ingeniería de software. Sin embargo, la generación del entorno existente cumplió

La noticia

arXiv:2601.13556v2 Announce Type: replace Abstract: Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout coherence), overlooking a crucial aspect: logical diversity from the testing perspective. This limits the comprehensive evaluation of embodied agent adaptability and planning robustness across distinct simulated environments. To bridge this gap, we propose LogicEnvGen, a novel method driven by Large Language Models (LLMs) that adopts a top-down paradigm to generate logically diverse simulated environments as test cases for agents. Given an agent task, LogicEnvGen first analyzes its execution logic to construct decision-tree-structured behavior plans