2 papers
cs.AI2026
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
Aagam Sogani, Botao Rui, Swetha Vaidyanathan +3
Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate confidently while still missi…
cs.CV2026
SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
Haotian Xia, Haonan Ge, Junbo Zou +16
Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models…