EUVIMEDEUVIMED entdecken
Crossref

TreeMind : Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search

Zhengyu Chen, Zhaoyi Meng, Wenxiang Zhao, Wansen Wang, Wenchao Huang, Jie Cui, Hong Zhong, Yan Xiong

ACM Transactions on Software Engineering and Methodology · 30.10.2026

DOI: 10.1145/3860893 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 30.10.2026. Verfasst von Zhengyu Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatically reproducing Android app crashes from textual bug reports is challenging, particularly when the reports are incomplete and modern UIs exhibit high combinatorial complexity. Approaches relying on reinforcement learning or large language models (LLMs) struggle to infer missing steps and reconstruct user action sequences in vast UI interaction spaces. We present TreeMind, which integrates LLMs with an adapted Monte Carlo Tree Search (MCTS) for strategic UI exploration in bug reproduction. TreeMind formulates the reproduction as a target-driven search problem and leverages MCTS to iteratively refine action sequences. To enhance MCTS with semantic reasoning, we introduce two LLM-guided agents: Expander generates promising actions based on the current UI state and exploration history, while Simulator estimates the likelihood that each candidate action leads toward successful reproduction using dynamic environment feedback. With multi-modal UI inputs and tailored prompts, TreeMind performs feedback-aware navigation that identifies essential user actions and incrementally reconstructs reproduction paths. We evaluate TreeMind on 100 Android bug reports, including 90 from three benchmarks and 10 from GitHub. Experimental results show that it outperforms four state-of-the-art baselines in reproduction success rate and average time cost over all runs, suggesting the promise of integrating LLM reasoning with MCTS-based planning for automated bug reproduction.

Zitieren

APA

Chen, Z., Meng, Z., Zhao, W., Wang, W., Huang, W., Cui, J., Zhong, H., & Xiong, Y. (2026). TreeMind : Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3860893

Vancouver

Chen Z, Meng Z, Zhao W, Wang W, Huang W, Cui J, et al. TreeMind : Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3860893

BibTeX
@article{Chen2026,
  author = {Chen, Zhengyu and Meng, Zhaoyi and Zhao, Wenxiang and Wang, Wansen and Huang, Wenchao and Cui, Jie and Zhong, Hong and Xiong, Yan},
  title = {TreeMind : Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3860893}
}
Kostenlos starten →