研究人员开发了 RGA-Designer，一种用于优化多智能体系统通信拓扑的新方法。该方法受人类反馈强化学习 (RLHF) 启发，使用奖励模型来平衡任务准确性和结构效率。通过使用此奖励模型对图生成器进行微调，RGA-Designer 在任务准确性方面达到了与 ARG-Designer 等先前方法相似的水平，同时平均令牌消耗减少了 20.5%。 AI
影响 减少了基于 LLM 的多智能体系统中的令牌消耗，可能降低运营成本并提高效率。
排序理由 该集群描述了 arXiv 论文中提出的一种用于优化多智能体系统的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2608.20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, h…
LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph g…
LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph g…