# Stanford 与 Together AI 论文提出 SAT：智能体团队自学协作策略，五项基准平均达 66.7%

- 来源：DAIR.AI (@dair_ai)
- 发布时间：2026-09-23 23:05
- AIHOT 分数：52
- AIHOT 链接：https://aihot.news/items/cmue9dkd70s9vrogho9vkynnl
- 原文链接：https://x.com/dair_ai/status/2102776257687781501

## AI 摘要

Stanford 和 Together AI 等机构的论文提出 Self-Organizing Agent Teams（SAT），让 o3-mini、Claude Sonnet 4 和 DeepSeek-V3 组成的团队从过往协作中学习可复用的协作策略。

## 正文

Banger paper from Stanford and Together AI.

They show why it might be a good idea to let your agent team learn its own way of working together.

(bookmark it)

Three models (o3-mini, Claude Sonnet 4 and DeepSeek-V3) averaged 66.7% across five math and physics benchmarks as a self-organizing team.

Their strongest member alone scored 48.8%, and a perfect router choosing among the members' independent answers scored 59.0%.

On AIME 2026 the team reached 71.2%, 13.4 points above that router.

One member reviews the team's earlier exchanges and rewrites the teamwork strategy, covering roles, the order of discussion phases, who participates and how partial answers are combined. The strategies were learned from only 15 AIME 2024 problems and then applied unchanged to held-out AIME 2024 problems and four new benchmarks.

Paper: https://academy.dair.ai/papers/self-organizing-agent-teams-learn-to-reason-together-2609.22682