analiza aiqbench
This preprint proposes scheduling when a language-model reviewer checks a frozen robot policy, reducing review calls as the system accumulates experience. The reported gains (57.2% lower reviewer token use, 80% to 97.19% success) come from four simulated manipulation tasks in a single preprint, so they need replication on real hardware and broader tasks. Still, the core idea of cutting supervision cost without retraining the policy is relevant to anyone building agentic robotics.
FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies
arXiv:2610.31427v1 Announce Type: new Abstract: Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in familiar situations. We introduce FastHarness, an experience-driven execution harness that adaptively schedules GPT-6 Astra supervision of a {\pi}0.5 policy. A fast path uses stage memory and reviewed outcomes to reduce review frequency as experience accumulates, while a complementary recovery path focuses supervision on correcting errors. Once recovery is verified, routine execution resumes, with failure experience retained to guide future interventions. The policy remains frozen and generates fresh actions from current observations. Across four simulated manipulation tasks, reviewer token use decreases by an average of 57.2% per task from the first evaluated episode to the mean of the final five episodes. Mean episode time decreases from 85.5 to 52.0 minutes over the same interval. On the same tasks, mean success increases from 80% for GPT-as-Policy ({\pi}0.5 + GPT-6 Astra) to 97.19% with FastHarness. These results highlight adaptive supervision as a practical route to more efficient agentic robotics without additional model training.
Abstract:Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in familiar situations. We introduce FastHarness, an experience-driven execution harness that adaptively schedules GPT-6 Astra supervision of a {\pi}0.5 policy. A fast path uses stage memory and reviewed outcomes to reduce review frequency as experience accumulates, while a complementary recovery path focuses supervision on correcting errors. Once recovery is verified, routine execution resumes, with failure experience retained to guide future interventions. The policy remains frozen and generates fresh actions from current observations. Across four simulated manipulation tasks, reviewer token use decreases by an average of 57.2% per task from the first evaluated episode to the mean of the final five episodes. Mean episode time decreases from 85.5 to 52.0 minutes over the same interval. On the same tasks, mean success increases from 80% for GPT-as-Policy ({\pi}0.5 + GPT-6 Astra) to 97.19% with FastHarness. These results highlight adaptive supervision as a practical route to more efficient agentic robotics without additional model training.
Robotics (cs.RO)
arXiv:2610.31427 [cs.RO]
(or arXiv:2610.31427v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.31427 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 269 cuvinte