Metraipolis › archive › dc_070bdb99c58a

GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions — arXiv:2609.34113

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34113
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:23.399Z
SHA-256 of the archived text
6721c04ace2fc38e80a94eda8d3de90841c8e12085edd3e86eeece1c83834a28
Stable URL of this page
https://metraipolis.com/documento/dc_070bdb99c58a

How to cite

GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions — arXiv:2609.34113 — arXiv (en), https://arxiv.org/abs/2609.34113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_070bdb99c58a (Metraipolis archive dc_070bdb99c58a, sha256 6721c04ace2fc38e80a94eda8d3de90841c8e12085edd3e86eeece1c83834a28)
BibTeX
@misc{dc070bdb99c58a,
  title = {GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions — arXiv:2609.34113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_070bdb99c58a; sha256 6721c04ace2fc38e80a94eda8d3de90841c8e12085edd3e86eeece1c83834a28},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding where and why Graphical User Interface (GUI) agents fail is essential for building more reliable systems, yet current evaluation relies on step accuracy, a metric that treats each screen independently and overlooks the underlying structure of GUI environments. This leads to two critical blind spots: (1) functionally equivalent screens are evaluated in isolation, obscuring systematic failure patterns across shared screens; and (2) the long-tailed GUI distribution renders failures on rare but critical screens invisible under standard metrics. To address these issues, we propose \textbf{GUITAR}, a state-centric diagnostic framework that performs structured failure analysis over both states and transitions, using a State Transition Graph (STG) by mapping visually diverse screens to shared functional states. Across 8 agents and 6 tasks from AndroidControl and Mind2Web, GUITAR reveals that 60.4\% of failures occur in 20\% of states, localizing errors to a small set of bottlenecks. Bottleneck-targeted guidance improves SR by 2.8\% and retains a 1.88\% average gain across 7 agents under three-fold trajectory-held-out evaluation with fully automatic STGs. These findings demonstrate the diagnostic and actionable value of structure-aware evaluation within the evaluated mobile and web tasks. Code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34113 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.433Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).