GUI-GENESIS：用于 GUI 代理后训练的自动环境合成与可验证奖励
摘要
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.
引用
@article{arxiv.2602.14093,
title = {GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training},
author = {Yuan Cao and Dezhi Ran and Mengzhou Wu and Yuzhe Guo and Xin Chen and Ang Li and Gang Cao and Gong Zhi and Hao Yu and Linyi Li and Wei Yang and Tao Xie},
journal= {arXiv preprint arXiv:2602.14093},
year = {2026}
}