RSI-Harness: Optimizing the Harness Optimizer via Recursive Self-Improvement

The performance of an LLM agent depends heavily on its harness, which manages the model's context, tool use and control flow. Recent approaches automate harness design, yet the improver that edits the harness is written by hand and never changes, so it cannot learn from the outcomes of its past edits. Self-referential systems relax this restriction by letting the improver update itself, but it remains unclear whether they learn a better improver or merely find a better task harness along one search trajectory. We address this question by making the improver itself an explicit optimization target, so that it learns from its own search experience and becomes a better optimizer. We realize this idea in RSI-Harness, a dual-loop recursive self-improvement framework in which an inner loop uses the current improver to refine the task harness, while an outer loop revises the improver from the history of successful and failed attempts. Each revision may start from any archived improver, and an acceptance gate adopts it only if it produces a better task harness than the current improver under matched tasks and budget. Across five benchmarks and three frozen backbones, RSi-Harness achieves the best average score on every backbone, improving the initial harness by 7.7 points on average with 69% fewer optimization tokens on average than competing baselines. More importantly, the improver itself recursively gets better, with its gain on the same starting harness growing from 1.3 to 6.2 points. The final improver also transfers to unseen models, benchmarks and domains, gaining at most 4.5$\times$ as much as the initial improver, while the optimized task harness transfers poorly.