GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training

TL;DR

GUI-GENESIS automatically creates efficient, verifiable GUI training environments from real applications, significantly reducing latency and costs while improving agent performance and enabling self-improvement pathways.

Contribution

It introduces a novel framework for synthesizing lightweight, verifiable GUI environments with code-native rewards, enhancing training efficiency and reliability.

Findings

Reduces environment latency by 10x

Cuts training costs by over $28,000 per epoch

Agents outperform base models and real-world RL baselines

Abstract

Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications is hindered by high latency, poor reproducibility, and unverifiable rewards relying on noisy visual proxies. To address the limitations, we present GUI-GENESIS, the first framework to automatically synthesize efficient GUI training environments with verifiable rewards. GUI-GENESIS reconstructs real-world applications into lightweight web environments using multimodal code models and equips them with code-native rewards, executable assertions that provide deterministic reward signals and eliminate visual estimation noise. Extensive experiments show that GUI-GENESIS reduces environment latency by 10 times and costs by over $28,000 per epoch compared to training on real applications. Notably, agents trained with GUI-GENESIS outperform the base model by 14.54% and even real-world RL baselines by 3.27% on held-out real-world tasks. Finally, we observe that models can synthesize environments they cannot yet solve, highlighting a pathway for self-improving agents.