Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation
Xuyang Li, Jianwu Fang, Lin Li, Boyuan Chen, Guangliang Li, Jianru Xue
Abstract
Recent advancements in multi-robot navigation have explored methods that combine Large Language Models (LLMs) for tasks like scene understanding or high-level decision-making. However, these approaches face challenges with high inference latency and potential hallucinations. To address these challenges, we propose a knowledge-driven Reinforcement Learning (RL) framework, GUIDER, that utilizes an LLM in two different offline roles. First, we leverage the LLM as an offline knowledge source. Its expertise is distilled into a compact model, which is applied only when the RL agent is uncertain about its own value estimates and the model itself is confident in its prediction. Additionally, we utilize the LLM as an offline semantic engine. This process translates the LLM
BibTeX
@inproceedings{aaai2026_guideddistillati,
title = {Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation},
author = {Xuyang Li and Jianwu Fang and Lin Li and Boyuan Chen and Guangliang Li and Jianru Xue},
booktitle = {AAAI 2026},
year = {2026}
}