AI RESEARCH
No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
arXiv CS.AI
•
ArXi:2604.23106v1 Announce Type: cross Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O test cases do not exist, and generating them requires solving the very problem at hand. To address this, we