AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third,

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T12:21:05.240Z. This is not the publication date.