LATIDIA · Robótica

FISRF: Marco de reflexión de andamiaje de instrucción flexible para la planificación de tareas de robótica con modelo de lenguaje grande

arXiv:2610.35686v1 Anuncio Tipo: nuevo Resumen: Los modelos de lenguaje grandes (LLM) se adoptan ampliamente para la corrección de errores reflexiva en la planificación de tareas; sin embargo, los enfoques existentes se basan principalmente en la exploración autónoma, ren

La noticia

arXiv:2610.35686v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous experiences during early interactions with new environments. To address this limitation, we propose the Flexible Instructional Scaffolding Reflection Framework (FISRF), an agent--mentor architecture that estimates the robot's Zone of Proximal Development (ZPD) in task planning and adaptively selects reflection strategies and mentor guidance, thereby facilitating the accumulation of effective error-correction experience. Experiments in ALFWorld and on real-world robotic platforms demonstrate that FISRF reduces the average number of error-correction rounds by 37% and redundant reasoning by 25.1%, while