Kimi 2.6 도입으로 Baseline 75% 달성 및 Skill Uplift 17.2pp 유지
Evaluating Kimi 2.5 vs Kimi 2.6: What happens to agent skills when the model gets smarter?
Evaluating Kimi 2.5 vs Kimi 2.6: What happens to agent skills when the model gets smarter?
The Five-Thousand-Line File
Context budget optimization: how to design MCP tools that don't waste tokens