# Test-Time Evolution of Reward Programs

InterEvolve introduces a test-time evolution framework in which an object-aware forward-backward (FB) behavioral foundation model executes reward programs, an LLM agent revises program structure in context while CMA-ES tunes its constants, and every candidate is verified across parallel simulation scenarios, letting a fixed humanoid controller solve untrained loco-manipulation tasks without retraining and raising macro-average success across eight task families from 34.6% for the best calibrated fixed program to 86.5%, with evolved skills deployed on a physical Unitree G1.

InterEvolve introduces a test-time evolution framework in which an object-aware forward-backward (FB) behavioral foundation model executes reward programs, an LLM agent revises program structure in context while CMA-ES tunes its constants, and every candidate is verified across parallel simulation scenarios, letting a fixed humanoid controller solve untrained loco-manipulation tasks without retraining and raising macro-average success across eight task families from 34.6% for the best calibrated fixed program to 86.5%, with evolved skills deployed on a physical Unitree G1.