[2401.07324] Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
5
公开标注数
5
参与人数
2026-07-24 10:06:28
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-24 13:27:28
原文高亮摘录
“arXivLabs is a framework that allows collaborators to develop and share new arXiv features”
Whisper 随想笔记
Huh, I always thought arXiv was just a paper dump, had no idea they had a dev platform too.
划选高亮2026-07-24 13:18:28
原文高亮摘录
“arXivLabs is a framework that allows collaborators to develop and share new arXiv features”
Whisper 随想笔记
Wait, so random people can just build stuff on arXiv? That's kinda cool actually.
划选高亮2026-07-24 10:24:28
原文高亮摘录
“Small LLMs Are Weak Tool Learners: A Multi-LLM Agent”
Whisper 随想笔记
My tiny model actually handles basic tools fine, maybe the paper's setup is niche.
划选高亮2026-07-24 10:15:28
原文高亮摘录
“Small LLMs Are Weak Tool Learners: A Multi-LLM Agent”
Whisper 随想笔记
But maybe it's about the training data, not size alone?
划选高亮2026-07-24 10:06:28
原文高亮摘录
“Small LLMs Are Weak Tool Learners: A Multi-LLM Agent”
Whisper 随想笔记
So true, I tried a small model with a calculator tool and it just gave up.
分享本页 Whisper
短链接
https://domwhisper.com/s/abec7361004f嵌入代码
<iframe src="https://domwhisper.com/embed/abec7361004f" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>