一个名为EvalCards的新框架被提出，用于标准化AI评估报告，解决了可重复性、可访问性和问责制问题。此外，一个名为Epi的自主研究代理通过在数学和算法任务中取得创纪录的成果，并在某些基准测试中超越Codex，展示了显著的进步。另外，一个用于定义和执行代理能力的框架Yara-L-Skill已被引入，使开发人员能够从可重用组件组合复杂行为。 AI
影响 这些发展为评估AI系统、增强自主研究能力和构建代理行为引入了新的工具和方法。
排序理由 该集群包含多篇与AI相关的研究论文和框架公告。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Low-bit quantization enables efficient deployment of large language models by reducing memory footprint and computational cost. Achieving high accuracy at low precision requires selecting quantization ranges, linear transformations, and weight rounding decisions. Existing approac…
arXiv:2512.22793v2 Announce Type: replace-cross Abstract: Reach-avoid (RA) games have significant applications in security and defense, particularly for unmanned aerial vehicles (UAVs). These problems are inherently challenging due to the need to consider obstacles, consider the …
arXiv:2511.21695v2 Announce Type: replace-cross Abstract: Evaluation reports guide the use of general-purpose AI (GPAI) models, yet inconsistent reporting often leaves essential questions unanswered. Through a review of prior work, we identify three central issues in evaluation r…
Épi is an autonomous research agent that maintains persistent investigations across sessions, improves through accumulated experience, and achieves record-setting mathematical and algorithmic results with reduced computational cost.
The engineering resources needed to maintain an application long-term usually differ from those needed to build it.
🧠 AgentSkill introduces Yara-L-Skill, a framework for defining and executing agent capabilities in a structured format. The system enables developers to compose complex behaviors through reusable skill components. 💬 Hacker News 🔗 https:// github.com/ajaynyayapathi/yara -l-skill #…