arXiv:2508. 18636v2 Announce Type: replace-cross Abstract: Representing a new paradigm in software distribution, LLM app stores are rapidly emerging, offering users diverse choices for content generation, coding assistance, education, and more.
arXiv:2601. 02430v3 Announce Type: replace-cross Abstract: Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential.
arXiv:2609.15387v3 Announce Type: replace-cross Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automat...
arXiv:2609.15387v1 Announce Type: cross Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evalu...
arXiv:2607. 28282v1 Announce Type: cross Abstract: Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive.
arXiv:2607. 20536v1 Announce Type: new Abstract: Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.
arXiv:2608. 08069v1 Announce Type: cross Abstract: Foundation models are increasingly reused as software components, making model selection a critical software-engineering decision.
arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.
arXiv:2606. 26429v1 Announce Type: new Abstract: Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better reflect open-ended user interactions.
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores.
arXiv:2608.22559v1 Announce Type: new Abstract: Rubrics aim to make language-model evaluation transparent by decomposing response quality into interpretable criteria. However, natural-language rubric...
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
The paper introduces Balance of Benchmarks (BoB), a framework that improves task-conditioned model comparison by weighting benchmark evidence based on semantic density, equating scores across varying difficulty levels, and pooling task-relevant residuals. BoB retains all eligible benchmark data while adjusting its influence, outperforming uniform averaging on the WildScores dataset with higher Spearman correlation, lower MAE, and better shortlist hit rates. The method also reduces ranking instability when benchmarks are repeated or paraphrased, and lowers retrospective regret in model selection.