3 papers
cs.CL2025
Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
Lingzhong Dong, Ziqi Zhou, Shuaibo Yang +6
Mobile-use agents powered by vision-language models (VLMs) have shown great potential in interpreting natural language instructions and generating corresponding actions based on mo…
cs.CL2025
From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests
Luoxi Tang, Tharunya Sundar, Yuqiao Meng +7
As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instea…
cs.AI2025
On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study
Shuai Yang, Qi Yang, Luoxi Tang +4
Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual…