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
Bowen Wang
3 articles on SOTA Papers
Qwen-CUA Reaches 86.2 on Verified Computer Use
A 397B-A17B mixture-of-experts agent learns screenshot-only keyboard and mouse control from verifiable interactive trajectories, improving OSWorld-Verified performance to 86.2.
Aug 8, 20264 min2608.02352
Long-Horizon Workflows Expose Agent Reliability Gaps
OSWorld 2.0 packages 108 multi-application workflows into executable tests, where the best tested agent completes only 20.6%.
Jul 28, 20265 min2606.29537