Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
This work addresses a critical bottleneck in multi-agent AI systems for researchers and practitioners, offering a novel approach to topology design that improves efficiency and robustness, though it is incremental in advancing existing methods.
The paper tackles the problem of designing communication topologies in LLM-based multi-agent systems to optimize collective decision-making, finding that moderately sparse topologies achieve optimal performance by balancing error suppression and beneficial information diffusion, with EIB-leanrner showing superior effectiveness, communication cost, and robustness in experiments.
The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent studies for communication topology automated design tend to construct sparse structures for efficiency, they often overlook why and when sparse and dense topologies help or hinder collaboration. In this paper, we present a causal framework to analyze how agent outputs, whether correct or erroneous, propagate under topologies with varying sparsity. Our empirical studies reveal that moderately sparse topologies, which effectively suppress error propagation while preserving beneficial information diffusion, typically achieve optimal task performance. Guided by this insight, we propose a novel topology design approach, EIB-leanrner, that balances error suppression and beneficial information propagation by fusing connectivity patterns from both dense and sparse graphs. Extensive experiments show the superior effectiveness, communication cost, and robustness of EIB-leanrner.