Preprint
Aug 2026
HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning
Experiments show that HypoForge consistently outperforms existing AI scientist frameworks and skill-level variants, and demonstrates the effectiveness of the proposed stage-specific skill learning paradigms.
Ziqing Qian, Jiaying Lei, Yi-Fang Wang et al.
· 0 citations