Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. However, they also face the inefficiency challenge as they process long sequences of high-resolution screenshots and solving long-horizon tasks, making inference slow, costly...
Kung-Hsiang Huang, Haoyi Qiu, Yu-Tong Dai et al.· Trans. Mach. Learn. Res.· 12 citations· ⚡3
Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existing harness-model co-evolution approaches improve both components, yet often treat trajectories produced during harness search as an undifferentiated replay buffer. This...
Ji-Xuan Chen, Jia-Xin Zhang, Qinyuan Ye et al.· 1 citation
Opera is presented, a verbal critic framework that treats each correction as a persistent note, followed until the diagnosed problem is resolved, and achieves the highest mean resolve rate among competitive critic baselines on all three benchmarks.
Kai Mei, Zhi-Yuan Hu, Yu-Tong Dai et al.· 0 citations
Grounding action, verification, and memory in state, what the authors call state-grounding, shifts the main bottleneck from perception toward reasoning: failures depend more on what the agent thinks than on what it sees.
Yan Yang, Xiang-Ru Jian, Ziyang Luo et al.· arXiv.org· 4 citations
DarwinX is introduced, which treats self-evolution as selection over a population of harnesses with the model frozen: a preserve-and-extend contract admits only variants that extend coverage without regressing, an archive keeps alternative lineages for recombination, and failure-, teacher-, and self-derived evidence sh...
Yifang Zhang, Yutong Dai, Juntao Tan et al.· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
