A colleague said something to me last year that I haven’t quite been able to shake. We were in a conversation about emerging markets, and he said, very genuinely, “It’s brilliant what’s happening in Africa with fintech. They’re really starting to catch up.” He meant it kindly. I didn’t correct him in the moment. But I’ve been thinking about it ever since, because the framing is so wrong it’s almost the opposite of what’s true. Africa isn’t catching […]

Ver mais

arXiv:2602.17848v1 Announce Type: new Abstract: Recent work has shown that larger language models have better predictive power for eye movement and reading time data. While even the best models under-allocate probability mass to human responses, larger models assign higher-quality estimates of next tokens and their likelihood of production in cloze data because they are less sensitive to lexical co-occurrence statistics while being better aligned semantically to human cloze responses. The results provide support for the claim that the […]

Ver mais

The all-cash deal gives MoEngage access to technology that assigns AI agents to individual customers.

Ver mais

arXiv:2603.05721v1 Announce Type: new Abstract: We consider the task of estimating the trace of a matrix function, ${rm tr}(f({bf A}))$, of a large symmetric positive semi-definite matrix ${bf A}$. This problem arises in multiple applications, including kernel methods and inverse problems. A key challenge across existing trace estimation methods is the need for matrix-vector products (matvecs) with $f({bf A})$, which can be very expensive. In this article, we introduce a novel trace estimator, FlexTrace, an exchangeable, single-pass method […]

Ver mais

arXiv:2602.07071v1 Announce Type: new Abstract: Open-source software (OSS) is foundational to modern digital infrastructure, yet this context for group work continues to struggle to ensure sufficient contributions in many critical cases. This literature review explores how artificial intelligence (AI) is being leveraged to address critical challenges to OSS sustainability, including maintaining contributor engagement, securing funding, ensuring code quality and security, fostering healthy community dynamics, and preventing project abandonment. Synthesizing recent interdisciplinary research, the paper identifies key applications of […]

Ver mais

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train vision-language-model(VLM) agents in interactive environments with a primary focus on performance, generalization remains underexplored due to the lack of standardized benchmarks and open-source RL systems. In this work, we formalize the problem as a Contextual Markov Decision Process (CMDP) and introduce textbf{AndroidWorld-Generalization}, a benchmark with three increasingly challenging […]

Ver mais

Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce SkillLearnBench, the first benchmark for evaluating continual skill learning methods, comprising 20 verified, skill-dependent tasks across 15 sub-domains derived from a real-world skill taxonomy , evaluated at three levels: skill quality, execution trajectory, and task outcome. Using this benchmark, we evaluate recent continual learning […]

Ver mais