Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination

TL;DR

This paper investigates whether large language model agents can effectively collaborate in multi-agent rescue tasks involving resource allocation, prioritization, and coordination, revealing their strengths and limitations in physically grounded scenarios.

Contribution

It introduces a structured victim rescue task for LLM agents, evaluates their multi-agent coordination abilities, and provides insights into their performance and failure modes in collaborative environments.

Findings

LLM agents can coordinate effectively in structured rescue tasks.

Performance varies with task complexity and urgency levels.

Identifies key failure modes and areas for architectural improvements.

Abstract

The ability to coordinate actions across multiple agents is critical for solving complex, real-world problems. Large Language Models (LLMs) have shown strong capabilities in communication, planning, and reasoning, raising the question of whether they can also support effective collaboration in multi-agent settings. In this work, we investigate the use of LLM agents to solve a structured victim rescue task that requires division of labor, prioritization, and cooperative planning. Agents operate in a fully known graph-based environment and must allocate resources to victims with varying needs and urgency levels. We systematically evaluate their performance using a suite of coordination-sensitive metrics, including task success rate, redundant actions, room conflicts, and urgency-weighted efficiency. This study offers new insights into the strengths and failure modes of LLMs in physically grounded multi-agent collaboration tasks, contributing to future benchmarks and architectural improvements.