קולבורציה יעילה של גורמים רב-אגנטים על ידי חלוקה מחשבתית מונחה-מערכת-אחד

תקציר מקורי באנגליתarXiv:2610.08155v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task selection, role assignment, message routing, and context management. As interactions grow, using powerful LLMs for these bounded control decisions introduces substantial token overhead and latency, limiting the scalability of agentic Web services. In this paper, we investigate whether coordination can be decoupled from expensive reasoning without compromising collaborative performance. We propose S1-MAS, a token-efficient mult