# Microsoft Research 论文研究测试时通信：k 个智能体团队媲美 4k 独立智能体

- 来源：elvis (@omarsar0)
- 发布时间：2026-09-23 23:35
- AIHOT 分数：52
- AIHOT 链接：https://aihot.news/items/cmue9rxdt0siwrogh7vkadlwl
- 原文链接：https://x.com/omarsar0/status/2102783808286384159

## AI 摘要

Microsoft Research 等机构的论文研究多智能体在任务执行中通过共享目录通信的收益。在 ARC-AGI-3 上，k 个通信智能体的成功率匹敌 4k 个独立智能体且差距随 k 扩大；在 polyomino packing 超越 best@k 和已知最优成绩，MNIST 压缩任务中四智能体团队写出 1,957 字节、99.4% 测试准确率的分类器。

## 正文

Banger paper from Microsoft Research and colleagues.

It studies the potential benefits of agents that share progress while they work.

(bookmark it)

Communication is still a challenge with multi-agent systems.

In this setup, agents have no predefined roles and communicate via a shared directory.

They report that a team of k agents that write their findings to a shared directory matches the success rate of 4k agents working independently on ARC-AGI-3.

The gap grows with k, and teams reliably solve some tasks that no single agent solves.

The same setup beat best@k on polyomino packing and exceeded the prior best-known score. On MNIST compression, a four-agent team wrote a 1,957-byte classifier with 99.4% test accuracy, smaller than the best-known human solution.

Independent agents still do better when compute is tight or when there is no clear measure of progress, so the paper also tells you when it might be a good idea to skip communication.

Paper: https://arxiv.org/abs/2609.21032

Chat with Paper: https://academy.dair.ai/papers/scaling-discovery-through-test-time-communication-2609.21032