ALMC: Adaptive LLM-based Multi-Agent Collaboration Across Diverse Task Domains

Feng He, Tianqing Zhu, Bo Liu, Dayong Ye, Zhen Fang, Huajie Chen, Wanlei Zhou

Keywords: LLM Agent, Dynamic LLM Multi-Agent Collaboration

Abstract: Large language model-based multi-agent systems (LLM-MAS) are effective at solving complex tasks by coordinating specialized agents. However, existing frameworks rely on a small set of predefined scenarios with static role configurations and rigid collaboration structures, limiting their adaptability across diverse task domains. We propose the Adaptive LLM-MAS Collaboration (ALMC) framework, which dynamically recruits agents and configures collaboration patterns according to task demands through three collaborative components: a Manager Agent that synthesizes task-specific role compositions and an executable workflow, a Judge Agent that evaluates execution quality, and a Solution Optimizer Agent that persists and reuses high-quality configurations via retrieval-augmented generation. The framework supports human-in-the-loop review and creates a learning loop where previous superior configurations improve future executions on similar tasks. By using ALMC, collaborations become adaptive, auditable, and reusable across domains. Code is available at: https://anonymous.4open.science/r/ALMC-2E0F.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 7088