Stout in Computer Science and Technology Studies

Articles

• Continual Red-Teaming and Guardrail Distillation for Tool-Using LLM Agents: Prompt-Injection Resistance with Utility Preservation

  Wesley Gao (Author)

  01-23

  • PDF

• Risk-Calibrated Multi-Resource Scheduling for Disaggregated AI Inference with LLM-Generated Evidence Memos

  Justin Yang (Author)

  24-46

  • PDF