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

2026-01-28

AI Summary

This work addresses the inefficiency of existing large language model (LLM)-based multi-robot collaboration approaches, which redundantly replan even for semantically similar tasks. To overcome this limitation, we propose a collaboration framework that explicitly perceives task similarity and enables planning reuse for tasks that are not identical but semantically related. Our approach integrates task similarity detection with a memoization mechanism to avoid redundant computation. We further introduce MeCoBench, the first benchmark specifically designed for evaluating multi-robot collaboration on semantically similar tasks. By combining LLMs with tailored similarity metrics and caching strategies, our method significantly reduces planning overhead and improves task success rates, outperforming current state-of-the-art approaches.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• multi-robot collaboration
• large language models
• task similarity
• memoization
• planning efficiency

Innovation

• memoization
• large language models
• multi-robot collaboration
• task similarity
• plan reuse