AI Hub
All papers
ArchitectureTrainingReinforcement LearningAgents

Kimi K2: Open Agentic Intelligence

Moonshot AI·July 28, 2025

Kimi Team

View on arXiv

TL;DR

A 1.04T-parameter MoE (32B active) trained on 15.5T tokens for agentic and tool-use tasks, introducing the MuonClip optimizer for stable trillion-scale training plus a large agentic-data synthesis and joint-RL pipeline.

Why it matters

A landmark open-weight agentic model; MuonClip drew major attention as a route to stable training at trillion-parameter scale.

Related models

Related terms