#Qwen-3.5-35B-A33

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "Qwen-3.5-35B-A33", newest first.

Sep 9

Composing post-trained Qwen agents achieves 72.6% success on SWE-bench, outperforming no-test baseline by 11.4 points without stronger models or Oracle feedback.

#ExecCritic #Qwen-3.5-35B-A3B #coding assistants #test generation

arXiv cs.AI@Leitian Tao et al. (10)Source