Metraipolis › archive › dc_8341bf899551
Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents — arXiv:2608.21830
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21830
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:38:59.705Z
- SHA-256 of the archived text
bf72c64ea572d8072af76869db1c288b437d0bd89df0db047e7e39e3f1ababc8- Stable URL of this page
https://metraipolis.com/documento/dc_8341bf899551
How to cite
Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents — arXiv:2608.21830 — arXiv (en), https://arxiv.org/abs/2608.21830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8341bf899551 (Metraipolis archive dc_8341bf899551, sha256 bf72c64ea572d8072af76869db1c288b437d0bd89df0db047e7e39e3f1ababc8)
BibTeX
@misc{dc8341bf899551,
title = {Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents — arXiv:2608.21830},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21830},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8341bf899551; sha256 bf72c64ea572d8072af76869db1c288b437d0bd89df0db047e7e39e3f1ababc8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diverse digital environments, where reinforcement learning (RL) has become a dominant training paradigm. However, widely used methods such as Group Relative Policy Optimization (GRPO) suffer from reward-gradient misalignment, leading to inefficient and unstable optimization. Recent work addresses this issue by reformulating RL with verifiable rewards (RLVR) as contrastive or classification-based objectives, which improve stability by eliminating problematic gradient behaviors. Despite this progress, existing contrastive RLVR methods rely primarily on outcome-level supervision and fail to capture fine-grained differences in trajectory quality within the same outcome category. In this paper, we propose Length-Aware Contrastive Learning for GUI Agents (LACL-GUI), a contrastive RLVR framework that incorporates trajectory-level quality signals into policy optimization. LACL-GUI introduces structured preferences within both successful and failed trajectories, encouraging concise successful executions and differentiating failure quality based on divergence from successful trajectories, while preserving optimization stability. Experiments on GUI agent benchmarks show that LACL-GUI provides more effective learning signals and consistently improves agent performance over prior methods, highlighting the value of trajectory-level supervision in contrastive RLVR. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.21830 — 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 2026-10-18T07:37:52.672Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).