AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
This addresses the need for more adaptable multi-agent systems in AI, though it is incremental by building on existing LLM-based collaboration methods.
The paper tackles the problem of inflexible communication in multi-agent collaboration by proposing a sequential framework with next-agent prediction and next-context selection, achieving superior performance and reduced communication overhead in benchmarks.
Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.