Article

TinyAstral: Transferring a self-evolving harness to small generalist manipulation agents

TinyAstral proposes a two-stage method: first freeze an open-weight teacher model and optimize its harness through recursive self-improvement (RSI), then distill a 4B student model to replace the teacher within the same harness. On RoboTwin, harness evolution raised the teacher's success rate from 33.4% to 63.6%, and the final 4B student reached 62.8%; in measured deployment episodes, the student used about one-fifth of the teacher's accelerator time.

Part of the event: TinyAstral: Self-Evolving Harness Transfer to a 4B Manipulation Agent

This page provides a summary and source link only.