Multi-robot systems have been widely deployed in real-world applications, providing significant improvements in efficiency and reductions in labor costs. However, most existing multi-robot collaboration methods rely on extensive task-specific training, which limits their adaptability to new or diverse scenarios. Recent research leverages the language understanding and reasoning capabilities of large language models (LLMs) to enable more flexible collaboration without specialized training. Yet, current LLM-empowered approaches remain inefficient: when confronted with identical or similar tasks, they must replan from scratch because they omit task-level similarities. To address this limitation, we propose MeCo, a similarity-aware multi-robot collaboration framework that applies the principle of ``cache and reuse'' (a.k.a., memoization) to reduce redundant computation. Unlike simple task repetition, identifying and reusing solutions for similar but not identical tasks is far more challenging, particularly in multi-robot settings. To this end, MeCo introduces a new similarity testing method that retrieves previously solved tasks with high relevance, enabling effective plan reuse without re-invoking LLMs. Furthermore, we present MeCoBench, the first benchmark designed to evaluate performance on similar-task collaboration scenarios. Experimental results show that MeCo substantially reduces planning costs and improves success rates compared with state-of-the-art approaches.

翻译：多机器人系统已在现实应用中广泛部署，显著提升了效率并降低了人力成本。然而，现有的大多数多机器人协作方法依赖于大量针对特定任务的训练，这限制了它们对新场景或多样化场景的适应性。近期研究利用大语言模型（LLMs）的语言理解和推理能力，实现了无需专门训练的灵活协作。然而，当前基于LLM的方法仍然效率低下：当面对相同或相似任务时，由于忽略了任务层面的相似性，它们必须从头开始重新规划。为解决这一局限，我们提出了MeCo，一种基于相似性感知的多机器人协作框架，该框架应用“缓存与重用”（亦称记忆化）原则以减少冗余计算。与简单的任务重复不同，识别并重用相似但不完全相同任务的解决方案更具挑战性，尤其是在多机器人场景中。为此，MeCo引入了一种新的相似性测试方法，能够检索高度相关的已解决任务，从而在不重新调用LLMs的情况下实现有效的规划重用。此外，我们提出了MeCoBench，这是首个专门用于评估相似任务协作场景性能的基准测试。实验结果表明，与现有先进方法相比，MeCo显著降低了规划成本并提高了任务成功率。