# RRSI: Regularized Recursive Self-Improvement of Agent Harnesses > Source: > Published: 2026-09-22 03:30:14+00:00 An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent ha