model-harness-co-evolution

CoEvo-RSI introduces a recursive self-improvement framework using bidirectional historical inheritance to align model capabilities with evolving agent harnesses, reducing brain-body mismatch. Using only SFT on rejection-sampled trajectories, it makes Qwen3.5-9B competitive with larger models, surpassing DeepSeek-V4-Pro and GLM-5.3 on agent benchmarks.

Introduces Recursive Harness Self-Improvement (RHI), a method that iteratively refines prompt-level harness specifications for AI agents using pairwise feedback, improving performance and reducing inference cost by up to 60% on diverse machine learning research tasks.