My Son's Math Homework Is Essentially Just Pokémon Education games are taking over American classrooms. One afternoon earlier this year, my 11-year-old son was sitting at his laptop and working quietly on his math homework. At least, that's what he was supposed to be doing. When I glanced at his screen, equations were nowhere to be seen. He was controlling a monster in the midst of battle, casting magic spells to outduel an opposing player.

This curation process is believed to be necessary to produce 5 performant models with broad zero-shot generalization abilities. However, as larger 6 models requiring pretraining on trillions of tokens are considered, it is unclear how 7 scalable is curation, and whether we will run out of unique high-quality data soon.

Do not distribute. 1 Introduction

We contend that utilizing existing relational databases is a promising approach to construct a benchmark that has both merits.

Our findings reveal that: I)LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III)Instruction-finetuning tends to increase the uncertainty of LLMs. These results underscore the significance of incorporating uncertainty into the evaluation of LLMs.

Previous research has reported that large language models (LLMs) demonstrate poor performance on the Chartered Financial Analyst (CFA) exams. However, recent reasoning models have achieved strong results on graduate-level academic and professional examinations across various disciplines. In this paper, we evaluate state-of-the-art reasoning models on a set of mock CFA exams consisting of 980 questions across three Level I exams, two Level II exams, and three Level III exams. Using the same pass/fail criteria from prior studies, we find that most models clear all three levels. The models that pass, ordered by overall performance, are Gemini 3.0 Pro, Gemini 2.5 Pro, GPT-5, Grok 4, Claude Opus 4.1, and DeepSeek-V3.1. Specifically, Gemini 3.0 Pro achieves a record score of 97.6% on Level I. Performance is also strong on Level II, led by GPT-5 at 94.3%. On Level III, Gemini 2.5 Pro attains the highest score with 86.4% on multiple-choice questions while Gemini 3.0 Pro achieves 92.0% on constructed-response questions.

With the advancement of computational resources, Large Vision-Language Models (LVLMs) exhibit impressive Perception and Reasoning (P&R) performance on Graphical User Interface (GUI) tasks. However, although they demonstrate strong P&R capabilities in English GUI scenarios, their performance in multilingual settings has received little attention, which limits their global applications. Moreover, existing studies on GUI tasks lack fine-grained analyses, including widget functions and elements' spatial relationships, which are fundamental for more targeted improvements. To tackle these issues, we propose MPR-GUI-Bench, a Multilingual fine-grained Perception and Reasoning GUI Benchmark to evaluate GUI agents' P&R capabilities. Evaluation results demonstrate that LVLMs exhibit significantly worse P&R performance in non-English languages than in English. To address these gaps, we propose GUI-XLI, a GUI Cross-Lingual Intervention method that applies interventions to the hidden states at P&R capability-related layers to mitigate the gaps between English and other languages, building on previous research showing that the hidden states of different language inputs exhibit significant differences in the latent space. Experimental results indicate that our method improves GUI agents' multilingual P&R capability by 6.5% on average.

Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks. In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific challenges. However, deploying LLMs as SaaS solutions raises data privacy concerns, while many open-source models demand significant computational resources for effective domain adaptation and deployment. A promising alternative is to develop smaller, domain-specialized LLMs, though this approach is often constrained by the lack of high-quality domain-specific training data. In this work, we address these limitations by presenting a cost-efficient and scalable training pipeline that combines guided synthetic data generation from a small seed corpus with bottom-up domain data curation. Our pipeline integrates Domain-Adaptive Pretraining (DAPT), Domain-specific Supervised Fine-tuning (DSFT), and Direct Preference Optimization (DPO) to train effective small-scale models for specialized use cases. We demonstrate this approach through DiagnosticSLM, a 3B-parameter domain-specific model tailored for fault diagnosis, root cause analysis, and repair recommendation in industrial settings. To evaluate model performance, we introduce four domain-specific benchmarks: multiple-choice questions (DiagnosticMCQ), question answering (DiagnosticQA), sentence completion (DiagnosticComp), and summarization (DiagnosticSum). DiagnosticSLM achieves up to 25% accuracy improvement over open-source models of comparable or larger size (2B-9B) on the MCQ task, while also outperforming or matching them in other tasks, demonstrating effective domain-specific reasoning and generalization capabilities.