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 (258B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces D-REX, a new benchmark with 8,162 adversarial samples for detecting deceptive reasoning in LLMs; primary contribution is the benchmark itself, with experimental validation on frontier models."
      4 }

Impressum · Datenschutz