Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
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.
ProofPaper ↗
Key points
- 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 multi-agent framework based on System One-guided computational division of labor.
Sources (1)
- [1]Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of LaborarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 11:11 AM
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.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 5, 2026Sharing AI progress in mathematics
- Oct 4, 2026nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
- Oct 2, 2026Chatham scales its capital markets expertise with OpenAI
- Oct 1, 2026Claude-shaped science
- Sep 29, 2026Introducing GPT-6.1 Sol
- Sep 28, 2026Holo4: powering generalist computer-use agents