AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

TL;DR

AnyMAC introduces a flexible, sequential multi-agent communication framework that enhances adaptability and efficiency by predicting the next agent role and selecting relevant context, outperforming static graph-based methods.

Contribution

The paper presents a novel sequential multi-agent collaboration framework with next-agent prediction and context selection, expanding communication topology and improving performance.

Findings

Achieves superior performance on multiple benchmarks.

Reduces communication overhead significantly.

Supports role flexibility and global information flow.

Abstract

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.