ai-research-survey

Systematic scan of agentic development research. What's signal, what's noise.
git clone https://git.shiptheloop.com/ai-research-survey.git
Log | Files | Refs

paper_type.json (324B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces JavaBench, a new project-level Java code generation benchmark with specific design (4 OOP projects, 389 methods, 106 classes), validated by student performance; LLM evaluation serves to establish benchmark utility rather than being the primary contribution."
      4 }

Impressum · Datenschutz