AI News
Self-HPO: alternating harness search and policy RL raises Qwen3.5-35B-A3B resolve rate 57.8% → 64.8%
Model Releases
Your complimentary preview is complete
Sign in to access the next engineering brief, save your reading history, and join the conversation.
Sign in to continueFree to join. Your place in this brief will be waiting.
0 Comments
Join the discussion.