Long-Horizon Agent

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents featured image
Computer-Use Agent

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

A five-platform framework and 250-task benchmark for evaluating hybrid computer-use agents that explore, build, and verify software recreations.

recreationworld-team-alibaba-token-hub-alibaba-group
•
Read more
Qwen3.8-Max: A New Bar for Coding and Cowork featured image
Long-Horizon Agent

Qwen3.8-Max: A New Bar for Coding and Cowork

Qwen 3.8-Max scales to 2.4 trillion parameters with comprehensive improvements across coding, work, research, and long-horizon tasks.

qwen-team-alibaba-group
•
Read more