作者位次 #3/12ICML 2026Poster· Deep Learning / Large Language Models
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
Boxi Yu · Yang Cao · Yuzhong Zhang · Liting Lin · Junjielong Xu · Zhiqing Zhong · Qinghua Xu · Guancheng Wang · Jialun Cao · Shing-Chi Cheung · Pinjia He · Lionel BRIAND