LLM多智能体系统仅需六种通信拓扑

6的平均分领先，比最强前代设计器高1.6分。

该系统在2.4毫秒内输出拓扑结构，使用21.

9%至33.2%更少的LLM token。

研究发现边数量与token消耗呈负相关，相关系数约为-0.4。

消息传递评分器在智能体共享配置文件时无法对候选进行排名。

Great paper on designing multi-agent systems. How many distinct communication topologies does an LLM multi-agent system actually need? This works claims that it's about six. Technical summary: Researchers grew the codebook capacity from 8 to 64 and the topologies that survived a reward filter kept collapsing to roughly the same six. Two further findings undercut the standard formulation. Edge count correlates negatively with measured token consumption at r about -0.4, so sparsifying the agent graph makes inference more expensive. And a message-passing scorer over agent-profile nodes is adjacency-invariant whenever agents share a profile, which is the default configuration in published benchmarks, so it cannot rank candidates at all in that regime. Codebook Agent drops the search entirely. A vector-quantized autoencoder compresses successful topologies into a query-independent 16-entry codebook, a reward-weighted MLP maps the query embedding to a distribution over codes, and an MLP proxy reading the flattened adjacency reranks the top decoded candidates in one batched forward pass. It emits a topology in 2.4 ms, leads all six benchmarks at 84.6 average against 83.0 for the strongest prior designer, and uses 21.9 to 33.2% fewer LLM tokens. Paper: arxiv.org/abs/2609.02264 Chat with Paper: academy.dair.ai/papers/codeboo…📊 2 ⚡

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include Codebook Agent, 多智能体系统, 通信拓扑, LLM.

Source attribution: curated from elvis (@omarsar0).