Kimi K2.5: Visual Agentic Intelligence (2026 · 66 citations)
Kimi K2.5 addresses two weaknesses of current agentic LLMs. Vision is often added to a text model late in training, and agents usually run tool calls one after another, so latency grows with task size. Built on Kimi K2, the model is jointly pre-trained on roughly 15 trillion mixed text and visual tokens. Vision is…
Kimi K3: Open Frontier Intelligence (2026 · 40 citations)
Open-weight LLMs have advanced quickly in reinforcement learning and test-time reasoning. However, most still sit near the 1T-parameter scale, so their pre-trained base models fall behind proprietary systems. Kimi K3 scales both pre-training and RL. It is a natively multimodal Mixture-of-Experts model with 2.8T total…

Co-authors here

12 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 191 times (of the 149,439 papers whose bibliographies we read); 13 citing papers with a page here →.

Updated 31 October 2026