研究库 论文知识库

内容库 / 论文

arXiv:2608.26730 · 工程化

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

类型：arxiv
标识：2608.26730
链接：https://arxiv.org/abs/2608.26730
主分类：engineering
形态：method
TLDR：Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposals. As evidence accumulates, a central problem emerges: which past update evidence remains actionable after subsequent training has changed the parent model? An update's effect depends on its parent, data, and training stage. Treating past success as context-free permission can waste compute. If the
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-04-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记精读与批判 · From 128K to 4M: Efficient Training of Ultra-Long Context LLMs

仓库 Dusto-AI/llm-situational-awareness-paper-list

仓库 PranayMahendrakar/arxiv-llm-analyzer

文档 Tom-on-flyP-2026-07-25

笔记 Cool Papers · cs.CL (papers.cool) · RSS 摘要

文档 Tom-on-flyP-2026-07-16

arXiv

2608.26730

TLDR

Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposals. As evidence accumulates, a central problem emerges: which past update evidence remains actionable after subsequent training has changed the parent model? An update's effect depends on its parent, data, and training stage. Treating past success as context-free permission can waste compute. If the

arXiv ↗ 中文全文