Today's trail

Interactive webpages underpin modern applications, but reproducing both their visual appearance and multi-step behavior remains challenging for multimodal large language models (MLLMs). Scalable training data must capture user actions, state transitions, and expected outcomes,…

Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic. To bridge this gap, we introduce the DAR-MGSM (Dialectal Arabic Multilingual Grade School Math) Benchmark, the first manually curated benchmark for evaluating mathematical…

Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagnostic metric framework for comparing how values are expressed and organized in human-reference and…