arXiv:2610.27205v1 Announce Type: new Abstract: Web agents are typically evaluated on English-language interfaces, leaving their ability to operate across the world's multilingual websites largely unexplored. This gap is especially significant for low-resource languages, where standardized resources for evaluating web agents remain limited. To address this gap, we introduce Low-Resource Web Agent Benchmark (LoWAgent), a benchmark for evaluating web agents across different low-resource languages
arXiv:2610.27227v1 Announce Type: new Abstract: Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill. Existing methods credit the skills present in each trajectory, yet presence is not responsibility: a harmful skill active in successful runs still earns positive credit. We present \textbf{GRSE}, \textbf{G}roup-\textbf{R}elative \textbf{S}kill \textbf{E}volution, which assig
arXiv:2610.27233v1 Announce Type: new Abstract: Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate them. We introduce MMedAgent-Plus, a multimodal medical tool-use agent that combines a vision-language planner with 18 leading specialist models spanning 12 tasks and 8 modalities. Through a unified tool interface, the planner selects specialists, executes them in sequence, and synthesizes responses groun
Hi V2EX, If you have opened TikTok this month you have probably seen the Bby Wow dance , which Spanish-speaking TikTok calls Dime Dime Baby : at a quinceañera party, a man in a cowboy hat walks out of the crowd toward the camera, bites his finger, brushes past the lens, walks away and comes back to point straight at you. Then people started remaking it with AI: same party, same moves, different dancer. I built a web tool that does exactly that, and I spent most of the time on result quality : Bb