EUVIMEDEUVIMED entdecken
Crossref

Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents

Yuan Zhao, Hualei Zhu, Tingyu Jiang, Shen Li, Xiaohang Xu, Hao Henry Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (43) · 36582-36590

DOI: 10.1609/aaai.v40i43.40981 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuan Zhao und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning and grounding capabilities, current methodologies exhibit two fundamental limitations: (1) insufficient exploitation of cross-model synergies, and (2) over-reliance on synthetic data generation without sufficient utilization. To address these challenges, we propose Co-EPG, a self-iterative training framework for Co-Evolution of Planning and Grounding. Co-EPG establishes an iterative positive feedback loop: through this loop, the planning model explores superior strategies under grounding-based reward guidance via Group Relative Policy Optimization (GRPO), generating diverse data to optimize the grounding model. Concurrently, the optimized Grounding model provides more effective rewards for subsequent GRPO training of the planning model, fostering continuous improvement. Co-EPG thus enables iterative enhancement of agent capabilities through self-play optimization and training data distillation. On the Multimodal-Mind2Web and AndroidControl benchmarks, our framework outperforms existing state-of-the-art methods after just three iterations without requiring external data. The agent consistently improves with each iteration, demonstrating robust self-enhancement capabilities. This work establishes a novel training paradigm for GUI agents, shifting from isolated optimization to an integrated, self-driven co-evolution approach.

Zitieren

APA

Zhao, Y., Zhu, H., Jiang, T., Li, S., Xu, X., & Wang, H. H. (2026). Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(43), 36582-36590. https://doi.org/10.1609/aaai.v40i43.40981

Vancouver

Zhao Y, Zhu H, Jiang T, Li S, Xu X, Wang HH. Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(43):36582-36590. doi:10.1609/aaai.v40i43.40981

BibTeX
@article{Zhao2026,
  author = {Zhao, Yuan and Zhu, Hualei and Jiang, Tingyu and Li, Shen and Xu, Xiaohang and Wang, Hao Henry},
  title = {Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {43},
  pages = {36582--36590},
  doi = {10.1609/aaai.v40i43.40981}
}
Kostenlos starten →