Moderately sparse communication topologies balance error suppression and insight propagation in LLM multi-agent systems, and the proposed EIB-Learner learns such topologies to outperform prior methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
Moderately sparse communication topologies balance error suppression and insight propagation in LLM multi-agent systems, and the proposed EIB-Learner learns such topologies to outperform prior methods.