Goal

Enable non-blocking experiment execution so the agent can continue higher-level research work while a long benchmark is in flight.

Implementation sketch

  • add a background: boolean mode to the experiment runner
  • spawn the benchmark process and return immediately
  • move metrics parsing and checks into an asynchronous completion path
  • notify the agent with a follow-up turn when the run finishes

Why this belongs in meta

This page is about the research harness, not about Parameter Golf model design itself.

Benefits

  • less idle time during long runs
  • cleaner separation between experimentation and synthesis
  • more opportunity to write or refine paper pages while the machine is busy