Agent Swarm Cuts Complex Task Latency Up To 4.5×
Kimi K2.5 couples joint text-vision training with dynamically scheduled parallel subagents, improving agentic search scores while reducing time to target quality.
Aug 13, 20264 min2602.02276
2 articles on SOTA Papers
Kimi K2.5 couples joint text-vision training with dynamically scheduled parallel subagents, improving agentic search scores while reducing time to target quality.
OSWorld 2.0 packages 108 multi-application workflows into executable tests, where the best tested agent completes only 20.6%.
