🤔 Does the communication topology for LLM multi-agent systems really need to be generated from scratch every single time? A team at UCLA questioned that very assumption. Title: Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems URL: ❓ Why have people assumed agent communication topologies need to be searched by a generative model every time? 💡 Turns out they may not need to be. The topologies that survive reward filtering converge to only about 6 distinct graphs, even as the codebook size grows from 8 to 64 — the design space is far smaller than it looks. ❓ Wouldn't making the graph sparser (fewer edges) cut down token usage? 💡 The opposite happens. Edge count correlates with token cost at r=-0.4 — sparser graphs actually use more tokens. Structural "cheapness" doesn't match measured cost. ❓ What's wrong with scoring candidate topologies using a GNN, as prior work does? 💡 For homogeneous agent teams (common in real deployments), the GNN's message passing treats every adjacency matrix as the same input, so it can't tell candidates apart — a real failure mode, not just a minor gap. ❓ So how well does Codebook Agent actually work once it swaps generation for selection? 💡 By compressing topologies into 16 codes via a VQ-AE and picking candidates with a reward-weighted MLP plus a proxy trained on real measured costs, it cuts generation latency from 301-396ms down to 2.4ms — a 125-158x speedup — while improving accuracy by 1.6 points on average over the prior best method and cutting tokens by 21.9-33.2%. #MultiAgent# #LLM#

“MindTopo: Can Foundation Models Reason in Topological Space?” Current models can recognize topological structure, but struggle to preserve it through sequential actions. And MindTopo exposes this reasoning–planning gap across 11K procedurally generated examples. They found that even image and video world models often reach plausible endpoints through topologically invalid trajectories.

Testing and evaluation is how serious science moves forward. Microsoft’s topological quantum system is now on site in Maryland, where DARPA will put the hardware through its paces. Here’s why that matters for the path to quantum at scale: