PulseAugur
EN
LIVE 12:09:45

New robot policy recipe ZAP achieves 96.7% success without real-world training

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a new robot control recipe called Zero-real Agent Policy (ZAP) that leverages a pretrained vision-language model. ZAP combines a 27B parameter model for world understanding with supervised fine-tuning and GRPO on simulated tasks for robot movement. This approach achieves 96.7% success on real-world tasks without any real-world robot data, outperforming existing models like MolmoAct2 VLA and matching GPT-6 Astra in speed and cost efficiency. AI

IMPACT This research demonstrates a novel method for training robot agents that significantly reduces the need for real-world data, potentially accelerating robotics development.

RANK_REASON Research paper detailing a new method for robot control. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New robot policy recipe ZAP achieves 96.7% success without real-world training

How we ranked this

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing a new method for robot control. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Benjamin Pikus, Daniel Saunders, Mircea Mironenco, Salman Mohammadi, Mathew Mathew, Sirou Zhu, Divya Makkar, Xuhua Huang, Qinbo Li, Supreeth Narasimhaswamy, Siyuan Cen, Thomas Neff, Dejia Xu, Shyamal Buch ·

    Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent

    arXiv:2610.35817v1 Announce Type: cross Abstract: A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introduce Zero-real Agent Policy (ZAP), a recipe that teaches a small off-…

RELATED ENTITIES

RELATED TOPICS