Event
FastHarness Experience-Driven Review Scheduling Framework Released
1 reports · 1 sources
The research team released the FastHarness robot execution framework: actions are generated by π0.5, reviewed and corrected by GPT-6 Astra, and the review interval is adjusted according to task stage and historical review results. The team claims that on multiple simulated manipulation tasks in RoboDojo, the framework achieves an average success rate of 97.19%, higher than the 80% reported for π0.5 + GPT-6 Astra in the GPT-as-Policy report. The framework does not train additional models; the weights of π0.5 remain unchanged, and only the supervision arrangement is adjusted. Multiple episodes of the same task share memory, and scene layouts vary. The above success rate is a result reported by the team on simulated tasks.
Report timeline
- FastHarness: A Robot Execution Framework That Schedules LLM Review Using Task Experience
FastHarness is an experience-driven robot execution framework that uses π0.5 to generate actions and GPT-6 Astra to review and correct them, adjusting the review interval according to task stage and past review results. Across four simulated manipulation tasks in RoboDojo, it achieved an average success rate of 97.19%, higher than the 80% reported for π0.5 + GPT-6 Astra in the GPT-as-Policy report.
CVer · 微信公众号 ·