Kimi K2.5 Tech Blog: Visual Agentic Intelligence
Kimi K2.5 defines Visual Agentic Intelligence. Trained on 15T tokens, it introduces SOTA visual coding and autonomous agent swarm. Read the full tech blog.
Kimi K2.5 Tech Blog: Visual Agentic Intelligence Kimi K2.5: Visual Agentic Intelligence Today, we are introducing Kimi K2.5, the most powerful open-source model to date. Kimi K2.5 builds on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens. Built as a native multimodal model, K2.5 delivers state-of-the-art coding and vision capabilities and a self-directed agent swarm paradigm. For complex tasks, Kimi K2.5 can self-direct an agent swarm with up to 100 sub-agents, executing parallel workflows across up to 1,500 tool calls . Compared with a single-agent set
saved by
related reading
- Kimi Agent Swarm: 100 Sub-Agents at Scalekimi.com
- Kimi K2.5: Visual Agentic Intelligence1kpapers.com
- Kimi K3 Tech Blog: Open Frontier Intelligencekimi.com
- GLM-5.2: Built for Long-Horizon Tasksz.ai
- Composer2.pdfcursor.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Kimi k1.5: Scaling Reinforcement Learning with LLMsalphaxiv.org
- Kimi-K2.5 Inference Benchmark - Luminalluminal.com
- Towards self-driving codebases · Cursorcursor.com
- frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
- Introducing SWE-2: Pushing the Pareto Frontiercognition.com
- Coding vs thinking — Paradigm 3paradigm3.org