-
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 139 -
An Empirical Study of Harness Design for Coding Agents
Paper • 2609.20804 • Published • 94 -
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Paper • 2609.24972 • Published • 228