作者位次 #4/8ACL 2026Poster· Natural Language Processing
Can We Predict Before Executing Machine Learning Agents?
Jingsheng Zheng · Jintian Zhang · Yujie Luo · Yuren Mao · Yunjun Gao · Lun Du · Huajun Chen · Ningyu Zhang
摘要
Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffers from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass the...