微软 Agensh 扩到 1024 个 Agent,pandoc 通过率升至 55%
MicrosoftResearch · hf · 2026-09-23
Microsoft Research introduced Agensh, a self-organized multi-agent harness with no central orchestrator, exploring agent count as a new scaling dimension.
- Motivation: existing multi-agent harnesses are often bottlenecked by a central orchestrator's capacity to allocate tasks. Agensh instead runs a cooperation loop where concurrent workers gather context, self-assign subtasks, act, share findings, verify, and merge progress asynchronously.
- Infrastructure: three components—a shared workspace for proposed/ongoing/completed work, a message interface for worker communication, and shared context retaining reusable findings and intentions.
- Results: on the five hardest ProgramBench tasks with GPT-5.6-sol (high), scaling from 1 to 128 agents raised mean test-pass rate from 19.31% to 28.78% (49% relative improvement); larger organizations reach comparable rates earlier.
- On pandoc, scaling from 1 to 1,024 agents lifted the pass rate from 33.89% to 55.06%. Worker trajectories show self-organized cooperation forms emerging and standardizing as the organization grows.
所属事件:微软发布自组织多智能体框架 Agensh(2 条相关)→
「编程与Agent」频道最新
- Vercel CEO 力挺 px0:面向 Agent 时代的轻量级代码审阅 IDE — arpit_bhayani · 2026-09-23
- Matt Pocock:与其追模型发布,不如打磨 agent 的运行环境 — mattpocockuk · 2026-09-23
- Uncle Bob：AI 没改变任何事，混乱越大项目越慢 — blaizedsouza · 2026-09-23
- GBrain 开源:把你的记忆、工具与技能接入任意 AI — garrytan · 2026-09-23
- 播客实测:用 AI 工具花 8 美元硬件做出小游戏 — aishashok14 · 2026-09-23
- 四轮实测发现：搜索预算耗尽前，Agent 从不点开原始来源 — memokris · 2026-09-23