CosmosMind releases MetaRSI-v1, a unified meta recursive self-improvement architecture, and open-sources RSI-Harness

MetaRSI-v1, a meta recursive self-improvement architecture, has been released by CosmosMind jointly with Tsinghua University, Peking University, Stanford University, UC Berkeley, MIT and other institutions. It unifies what the team calls model-level, data-level and harness-level recursion, aiming to improve the process of self-improvement rather than a single model.

With no external teacher model, a 3B active-parameter model (Qwen3.5-35B-A3B) averaged a 10.9-point improvement across Terminal-Bench 2.1, SWE-bench Pro, a GPQA-Diamond subset and AIME; six frontier flagship models averaged a 7.3-point gain on Terminal-Bench 2.1. The RSI-Harness is open-sourced, and the collaboration plans to extend the loop to programmable instruments and automated labs.

Original sources (Chinese)