Kimi 推出 Agent Swarm：让 100 个 AI 智能体为你工作
2025 年，如果你走进任何一场 AI 会议，可能会听到同样的福音：更快的推理速度、更长的上下文窗口、更低的推理成本。
这就像我们花了多年时间打磨锤子，让它更轻、更坚固、平衡更精准，却从未质疑过这样一个事实：木匠仍然只有两只手，一天仍然只有二十四小时。
现在，Kimi 推出了 Agent Swarm。它不是一把更好的锤子。它是对整个工作坊的重构。
这不是一个关于"多个 AI 智能体协同工作"的故事。我们正在构建的是一个拥有老板、员工和分工的组织结构，只不过这个组织并非由人类设计。它自行设计。
当你让 Agent Swarm 研究某个课题时，你并不是在指挥一个助手。你是在聘请一位 CEO，它会自行找到研究员、分析师、事实核查员——所有这些角色都由它当场招募。而你无需进行微观管理。
但要实现这一点，我们必须直面一个过去一直回避的问题：
单智能体推理的局限性
在测试阶段，我们究竟能把一个模型推到多远？
这个问题其实与智能无关。当今 AI 推理的真正瓶颈，恰恰是单智能体、顺序执行的模型本身。
无论你是试图延长模型能处理的任务长度（研究人员称之为长周期任务），还是在推理过程中动态扩展计算量和结构（测试时扩展），单智能体顺序执行模型都会撞上一堵墙。
例如，让一个单智能体深度研究工具调查一百家公司，或综合数十篇论文。随着任务推进，上下文窗口被填满。系统只能退而求其次，通过简单的历史折叠或摘要来为新 token 腾出空间。这种压缩是有损的，后续的推理质量也会下降。
这不是一个 bug，也不是暂时的局限。这是由上下文窗口、时间以及依赖单一智能体管理长周期推理的约束所共同构成的结构性天花板。
向外扩展，而非仅仅向上扩展
多年来，AI 领域的主流叙事一直是规模化：更大的模型、更多的参数、更优的基准测试分数。这一叙事确实带来了显著成果。但纵向规模化存在天花板——物理上的、经济上的，或许还有智力上的。
横向规模化则不同。一个大脑 vs 多个大脑。单个模型只是一名专家。而一个自组织网络则是一个公司、一个实验室、一个情报机构。
2025 年 6 月，在我们推出 Kimi Researcher 后不久，团队里一位成员——我们姑且称她为“热心业余股票交易员”——产生了一个看似简单的想法：Kimi 能否自动收集每日股票信息？
她让 Kimi 查看新闻以了解宏观趋势。查询历史涨停次数。若条件匹配则深入挖掘。进行综合。她编写了一个 Python 工作流，一串 if-else 语句的级联。
写到第一百行时，她停了下来。“我这是在手动编写一个多智能体系统。”
如果模型能够使用工具并处理长周期任务，为什么它们不能自己构建架构？决定何时并行、雇佣谁、如何委派？
未来不在于更好的单一智能体，而在于能够构建组织的智能体。Agent Swarm 正是源于这一假设。
数据说明了部分情况。借助 Agent Swarm，Kimi K2.5 能够：
- 部署多达 100 个并行工作的子智能体
- 执行超过 1,500 次工具调用
- 以比顺序执行快 4.5 倍的速度提供更优结果
Agent Swarm 最佳实践
显然，Agent Swarm 在可并行化的工作中表现出色：广泛调研、批量下载、多文件处理、多角度分析、长文写作。
但更深层的收益是结构性的——它创造了产生建设性分歧的条件：让独立的智能体得出不同结论，然后强制进行调和。它在结构上避免了群体思维。
因此，在以下场景中，我们建议您体验智能体集群的魔力。
规模化发现
从最简单的场景开始：寻找大量难以找到的东西。
假设您需要 100 个小众 YouTube 领域中各自排名前三的创作者。K2.5 Agent Swarm 首先研究并定义每个领域，然后自主创建 100 个子智能体进行并行搜索。
或者你想收集保罗·格雷厄姆全部 200 多篇文章，它们散落在个人网站、旧博客和转录的演讲中。K2.5 智能体集群可以分配专门的子智能体去搜索、下载、分类、总结并整理保罗·格雷厄姆的文章。它们共同将 200 多篇原创文章整理到 6 个按主题分类的文件夹中，并生成一份全面的总结报告。
100 个子智能体搜寻创作者：https://www.kimi.com/share/19c40eea-b272-8ef2-8000-0000af5e0baa
规模化输出
除了收集零散的信息，你还可以让智能体集群处理海量文档集，并协调专家角色，以生成书籍级别的专业报告。
例如，让它根据 40 份社会心理学 PDF 生成一份 100 页的文献综述。K2.5 智能体集群将任务分解到整个文档集中，部署多个专注于写作的子智能体。每个子智能体负责特定章节，它们的输出被整合成一份 100 页、双栏排版的学术文档，并包含完整的格式引文和参考文献。
从 40 份 PDF 生成 100 页文献综述：https://www.kimi.com/share/19c4106b-89b2-8361-8000-0000d07b8235
规模化视角
最有趣的用例是当你需要分歧本身时——当你希望同时从多个视角审视一个问题时。
面对复杂的产品发布？部署一个专家团队：持怀疑态度的 VC 质疑单位经济模型，资深 PM 担忧技术债务，伦理学家探究暗黑模式，客户成功负责人为边缘案例辩护。
让专家团队评审你的产品计划：https://www.kimi.com/share/19c40bc9-31a2-8533-8000-0000bad59b7a
或者探索不同的故事发展方向。你可以让 20 位来自不同文学风格的作家续写刘慈欣的《三体》：从弗吉尼亚·伍尔夫式的内心独白，到博尔赫斯式的思想迷宫，卡夫卡式的荒诞世界，以及加夫列尔·加西亚·马尔克斯式由重复命运塑造的故事。
让 20 位作家为《三体》创作不同结局：https://www.kimi.com/share/19c409c8-8692-821a-8000-0000070ad369
现已面向高级订阅用户开放
你曾经拥有一个勤勉的研究员——Kimi Agent。现在，你拥有一个专家团队——Kimi Agent Swarm：它们各司其职、并行工作，并且能够同时持有相互矛盾的观点。
这是一个早期的研究预览版。我们将持续加固其架构，引入子智能体间的直接通信、并行宽度的动态控制——但基础已就绪，足以应对你最严苛的工作。
在人工智能时代，素养或许可以用我们使用了多少模型 token 来衡量。
所以，输入你的提示词，让 Kimi 为你自主调度 100 个子智能体：https://www.kimi.com/agent-swarm
Kimi Introduces Agent Swarm: Let 100 AI Agents Work for You
In 2025, if you walked into any AI conference, you may hear the same gospel: faster inference, longer context windows, cheaper inference costs.
It's as if we've spent years perfecting the hammer, making it lighter, stronger, more precisely balanced, while never questioning the fact that the carpenter still has only two hands and twenty-four hours in a day.
Now, Kimi introduces Agent Swarm. It is not a better hammer. It is a reconstruction of the entire workshop.
This is not the story of "many AI agents working together". What we're building is an organizational structure with bosses, employees, and divisions of labor, except this organization isn't designed by humans. It designs itself.
When you tell Agent Swarm to research a topic, you aren't commanding an assistant. You are hiring a CEO, who helps find researchers, analysts, fact-checkers, all hired on the spot on its own. And you don't need to micromanage.
But to get there, we had to confront a question that we used to avoid:
The Limits of Single-Agent Reasoning
How far can we really push a model at test time?
This question isn't really about intelligence. The real bottleneck in AI reasoning today is the single-agent, sequential execution model itself.
Whether you're trying to extend the length of tasks a model can handle (what researchers call long-horizon tasks), or dynamically scaling compute and structure during inference (test-time scaling), the single-agent sequential execution model hits a wall.
For example, ask a single-agent deep research tool to survey a hundred companies or synthesize dozens of papers. As the task goes on, the context window fills. The system falls back to simple history folding or summarization to make room for new tokens. This compression is lossy, and later reasoning degrades.
It's not a bug, nor a temporary limitation. It's a structural ceiling imposed by context windows, time, and the constraints of relying on a single agent to manage long-horizon reasoning.
Scale Out, Not Just Up
For many years, the dominant narrative in AI has been scaling: bigger models, more parameters, better benchmark scores. This narrative has delivered remarkable results. But vertical scaling has a ceiling—physical, economic, and perhaps intellectual.
Horizontal scaling is different. One brain versus many. A single model is one expert. A self-organizing network is a company, a laboratory, an intelligence agency.
In June 2025, shortly after we launched Kimi Researcher, a member of our team — let's call her an "enthusiastic amateur stock trader"—had an idea that seemed simple enough: Could Kimi automatically gather daily information about stocks?
She let Kimi check news for macro trends. Query historical limit-up counts. Drill deeper if conditions match. Synthesize. She wrote a Python workflow, a cascade of if-else statements.
At line one hundred, she stopped. "I'm hand-coding a multi-agent system."
If models can use tools and handle long-horizon tasks, why can't they architect themselves? Decide when to parallelize, whom to hire, how to delegate?
The future isn't better single agents. It's agents that build organizations. Agent Swarm was born from this hypothesis.
The numbers tell part of the story. With Agent Swarm, Kimi K2.5 can:
- Deploy up to 100 sub-agents working in parallel
- Execute over 1,500 tool calls
- Deliver better results 4.5x faster than sequential execution
Agent Swarm Best Practices
Obviously, Agent Swarm excels where work parallelizes: broad research, batch downloads, multi-file processing, multi-angle analysis, long-form writing.
But the deeper benefit is structural, it creates the conditions for productive disagreement — for independent agents to arrive at different conclusions, then force a reconciliation. It avoids groupthink structurally.
So in the following cases, we suggest you experience the magic of agent swarm.
Discovery at Scale
Start with the simplest case: finding a mountain of things that are hard to find.
Say you need the top 3 creators in 100 niche YouTube domains. K2.5 Agent Swarm first researches and defines each domain, then autonomously creates 100 sub-agents to conduct parallel searches.
Or you want to collect all 200+ Paul Graham essays, scattered across personal sites, old blogs, transcribed talks. K2.5 Agent Swarm can assign specialized sub-agents to search for, download, categorize, summarize, and compile Paul Graham's essays. They collectively organize over 200 original essays into 6 topic-based folders and produces a comprehensive summary report.
100 Sub-agents Hunting for Creators: https://www.kimi.com/share/19c40eea-b272-8ef2-8000-0000af5e0baa
Output at Scale
Beyond gathering scattered information, you can task Agent Swarm with consuming massive document sets and coordinating expert personas to produce book-length, professional-grade reports.
For example, let it generate a 100-page literature review from forty social psychology PDFs. K2.5 Agent Swarm decomposes the task across the document set, deploying multiple writing-focused sub-agents. Each claims responsibility for specific sections, and their outputs are synthesized into a 100-page, two-column academic document with fully formatted citations and references.
Generate 100-Page Literature Review from 40 PDFs: https://www.kimi.com/share/19c4106b-89b2-8361-8000-0000d07b8235
Perspective at Scale
The most interesting use case is when you need the disagreement itself—when you want to see a problem through multiple perspectives at once.
Facing a complex product launch? Deploy a team of experts: the skeptical VC questions unit economics, the veteran PM worries about technical debt, the ethicist probes dark patterns, customer success lead champions edge cases.
Get your product plan reviewed by a team of experts: https://www.kimi.com/share/19c40bc9-31a2-8533-8000-0000bad59b7a
Or explore different story directions. You can have 20 writers from different literary styles to continue Liu Cixin's The Three-Body Problem: from Virginia Woolf–style inner monologues to Borges-like idea mazes, Kafkaesque absurd worlds, and Gabriel García Márquez–style stories shaped by repeating fate.
Let 20 writers create alternative endings for The Three-Body Problem: https://www.kimi.com/share/19c409c8-8692-821a-8000-0000070ad369
Now Available to Top Tier Subscribers
You once had Kimi Agent as a single, diligent researcher. You now have Kimi Agent Swarm as a team of experts: specialized, parallel, capable of holding contradictory viewpoints simultaneously.
This is an early research preview. We will continue to harden the architecture, introducing direct sub-agent communication, dynamic control of parallel width—but the foundation is ready for your most demanding work.
In the AI age, literacy may be measured by how many tokens we use.
So type your prompt, and let Kimi self-direct 100 sub-agents for you: https://www.kimi.com/agent-swarm