Steve-Evolving: Open-World Embodied Self-Evolution via Fine-Grained Diagnosis and Dual-Track Knowledge Distillation

ArXi:2603.13131v1 Announce Type: new Open-world embodied agents must solve long-horizon tasks where the main bottleneck is not single-step planning quality but how interaction experience is organized and evolved. To this end, we present Steve-Evolving, a non-parametric self-evolving framework that tightly couples fine-grained execution diagnosis with dual-track knowledge distillation in a closed loop. The method follows three phases: Experience Anchoring, Experience Distillation, and Knowledge-Driven Closed-Loop Control.