MeCo: Enhancing LLM-Empowered Multi-Robot Collaboration via Similar Task Memoization

TL;DR

MeCo enhances multi-robot collaboration by using a similarity-aware memoization approach with LLMs, significantly reducing planning costs and increasing success rates in similar-task scenarios.

Contribution

This paper introduces MeCo, a novel framework that applies similarity testing and memoization to improve LLM-based multi-robot collaboration efficiency.

Findings

Reduces planning costs by up to 50%.

Increases success rates in similar-task scenarios.

Introduces MeCoBench, a new benchmark for evaluation.

Abstract

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.