ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration

Abstract-- Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: declarative methods lack adaptability in dynamic environments, while iterative methods incur prohibitive computational costs that scale poorly with team size and task complexity. In this paper, we propose ELHPlan, a novel framework that introduces Action Chains--sequences of actions explicitly bound to sub-goal intentions--as the fundamental planning primitive. ELH-Plan operates via a cyclical process: 1) constructing intention-bound action sequences, 2) proactively validating for conflicts and feasibility, 3) refining issues through targeted mechanisms, and 4) executing validated actions. We further propose comprehensive efficiency metrics, including token consumption and planning time, to more holistically evaluate multi-agent collaboration. Our experiments on benchmark TDW-MA T and C-W AH demonstrate that ELHPlan achieves comparable task success rates while consuming only 24% of the tokens required by state-of-the-art methods. Our research establishes a new efficiency-effectiveness frontier for LLM-based multi-agent planning systems. Coordinating multiple robots to collaboratively accomplish complex tasks in dynamic environments represents a fundamental challenge in modern robotics, requiring sophisticated planning algorithms, effective communication protocols, and robust coordination mechanisms. Recent advances in Large Language Models (LLMs) have marked a significant step towards intelligent robotics, endowing robots with ability to understand natural language instructions and reason about complex action sequences in collaborative environments.