2 papers
cs.AI2026
Open-Endedness Bench: Measuring Epistemic Process from Agent Records
Chengyang Shi, Xianglin Ji, Jintao Huang +3
Agents are increasingly given open-ended research tasks: discovering an empirical law from self-designed experiments, improving a heuristic whose optimum nobody knows, or beating a…
cs.HC2026
A11yLTLNav: Automatic Detection of Accessibility Navigation Failures
Chenming Ge, Kewen Peng, Chengyang Shi +2
For blind and low-vision (BLV) screen-reader users, a website that appears accessible in a static snapshot can become difficult or impossible to navigate once interaction begins. Y…