微软研究院发布 Agensh：千级编码智能体无中心协同框架
微软研究院的 Agensh 论文，不用中央调度器，让 1000 多个编码智能体靠共享状态自己协作，pandoc 任务通过率从 33.89% 干到 55.06%，玩法挺新鲜。
微软研究院提出 Agensh，一个无中央编排器的多智能体框架，编码智能体通过共享工作区和消息通道异步认领子任务并合并结果。在 ProgramBench 五个最难任务上配合 GPT-5.6-sol，智能体数量从 1 增至 128 时，平均测试通过率从 19.31% 提升到 28.78%。在 pandoc 任务上，1,024 个智能体将通过率从 33.89% 提高到 55.06%。论文还记录了智能体自发形成的协作行为，这些行为随团队规模扩大逐渐成为惯例。
Banger paper from Microsoft Research. (bookmark it) They run 1K+ coding agents at once to test a scalable self-organized multi-agent harness. This is an interesting test because most multi-agent systems today have some hierarchy or structure. Agensh has no central orchestrator. It coordinates parallel coding agents through a shared state instead of a central orchestrator. Each agent gathers context, claims a sub-task, does the work, shares what it found, verifies the result, and merges it, all asynchronously through a shared workspace and a message channel. On the five hardest ProgramBench tasks with GPT-5.6-sol, increasing agents from 1 to 128 raises the mean final test-pass rate from 19.31% to 28.78%. Larger teams also reach a given pass rate sooner. On pandoc, 1,024 agents take the test-pass rate from 33.89% to 55.06%. The authors also report forms of cooperation that the agents start on their own and that become standard practice as the team grows. Paper: arxiv.org/abs/2609.26781 Chat with Paper: academy.dair.ai/papers/agensh-… 💬 42 🔄 30 ❤️ 233 👀 19256 📊 112 ⚡
