Hugging Face Papers ↗ · 2026-11-17
Do LLM Agents Still Need to Be Told How to Self-Improve?
媒体报道 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves.
全文
Capable frozen LLM agents can autonomously construct context-based self-learning algorithms from basic resources and a general goal, yielding text artifacts that transfer to new game and 3D navigation tasks.
正文以来源语言显示。