Saved in:
Bibliographic Details
Main Authors: Silva, João Vitor de Carvalho, Macharet, Douglas G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912545640546304
author Silva, João Vitor de Carvalho
Macharet, Douglas G.
author_facet Silva, João Vitor de Carvalho
Macharet, Douglas G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
Silva, João Vitor de Carvalho
Macharet, Douglas G.
Robotics
Artificial Intelligence
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.
title Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2508.14635