微软研究院发布 Agensh：千级编码智能体无中心协同框架

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-…📊 112 ⚡

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」「中美大模型技术代差与商业化对照」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：Agensh、GPT-5.6-sol、多智能体、ProgramBench，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 2 家独立信源对该事件进行交叉印证与跟进报道（含 AIGCLINK 等），属于近期高关注度行业信号。