牛哥精选 · 半年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 Dev.to 2026-06-26

Trace-to-Training: how agent runs become learning data

Agent运行轨迹转化为训练数据，IFEVAL评测提升8.7个百分点，方差降低提升生产可靠性。

Trace-to-Training: how agent runs become learning data Every agent run is a data point. Most frameworks throw it away. WasmAgent keeps it — evaluated …

agent 训练数据 ifeval qwen2.5 benchmark

📝 深度技术 arXiv AI 2026-06-11

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

新数据集与LoRA微调Qwen2.5突破古典诗歌翻译和情感语义理解瓶颈，技术细节值得深挖。

arXiv:2606.12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical C…

古典诗歌翻译情感语义理解 lora微调 qwen2.5 新数据集

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Trace-to-Training: how agent runs become learning data

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

📅 日期