Kuaishou Large Model

Oct 11, 2025 · Artificial Intelligence

How Large-Scale Reinforcement Learning Boosted KAT-Dev-72B-Exp to 74.6% on SWE‑Bench

The KwaiPilot team introduced KAT-Dev-72B-Exp, an open‑source LLM trained with large‑scale reinforcement learning that achieved a record‑breaking 74.6% score on SWE‑Bench Verified, thanks to innovations like Trie Packing, entropy‑aware advantage scaling, and a decoupled data‑environment architecture.