Open-source multimodal agentic model designed to advance general agentic intelligence. Features joint text-vision optimization and Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently, reducing latency by up to 4.5x over single-agent baselines. 1.1T MoE with 32B active parameters. Built on the Kimi K2 base.

Outputs 2

Kimi K2.5

model
Architecture MOE
Parameters 1.1T
Active params 32B

Kimi K2.5: Visual Agentic Intelligence

paper

arXiv: 2602.02276

moefrontieropen-weightagenticmultimodalreasoning