微软研究院论文：共享进度的多智能体团队可用更少数量追平独立智能体

结果显示 k 个智能体的团队在 ARC-AGI-3 上的成功率能追平 4k 个独立工作的智能体，且差距随 k 增大而扩大。该团队配置在 polyomino packing 任务上超过 best@k 并刷新此前最好成绩，在 MNIST 压缩任务上四智能体团队写出 1,957 字节、测试准确率 99.

4% 的分类器，比已知最好的人工方案更小。论文同时指出当算力紧张或缺乏清晰进度指标时，独立智能体表现更好。

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: arxiv.org/abs/2609.21032 Chat with Paper: academy.dair.ai/papers/scaling…📊 18 ⚡

本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：Microsoft Research、多智能体、ARC-AGI-3、arXiv，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「elvis」（@omarsar0），经 AITOP 多维评分管线结构化提炼。截至目前，全网已有 3 家独立信源对该事件进行交叉印证与跟进报道（含 Microsoft Research、arXiv: OpenAI 等），属于近期高关注度行业信号。